{"as_of":"2026-08-04T05:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:baa627c015317e98dff66a8474f3ea117a0b6a5d5e5c7a4bf89aeaec26c21fb2","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-13T10:21:01.818157Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+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/2604.04999/citation-record","integrity":"/paper/2604.04999/integrity","json":"/paper/2604.04999/citation-record.json","paper":"/paper/2604.04999"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Machine learning and AI in cancer prognosis, prediction, and treatment selection: A critical approach,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:54410a9ecfd25c159a7c8aceb8ac0cf27bc784eeb4e3162ad2f02859e0b02f6c","observation_id":"0aa3a483-609f-4705-8b5b-1631d68f16f2","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multivariable prognostic models: issues in developing models, evaluating assumptions and ade- quacy, and measuring and reducing errors,","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:4b0530ec2685cd1bdae9acdab4687c54010a9c72cca910669a2cabf4ce2c764e","observation_id":"c5866dae-25d0-453f-b840-e0ec8531e9d9","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Harnessing multimodal data integration to advance precision oncology,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:5812b370ac87a0dcb736f11a4fd73a09994fd54ee8d1b23d67e5d0b0effe2f14","observation_id":"3f8f5c65-d9cd-4fe5-a798-b9f239c482b2","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Review the cancer genome atlas (TCGA): an immeasurable source of knowledge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:67174b16a6ffe7f0ee5ec3c09761f247cf5eae14bd7c07d75d6bf0eab26eb0d4","observation_id":"cb7a688a-fd63-4885-a438-184afeed9f2d","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"A multimodal knowledge-enhanced whole-slide pathology foundation model,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:6aa27356d31ff461e376eed0cacc901cd863d180ed4f7aac9bbb32cf9e36c398","observation_id":"6cf55c99-f874-4a8d-82f9-60ec4adc523b","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Cross-modal translation and alignment for survival analysis,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:22c8cdc4c3967b73c4be1f0ecb7dc4c28ce9b78703a0e4c98f9ebbdabfa07049","observation_id":"b4e350c5-7b1a-402d-ab6f-f749119ccc40","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"PS3: A multimodal transformer integrating pathology reports with histology images and biological pathways for cancer survival prediction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:abe66fdd4d246b71928060ca86922516e1b7d8dbda8ac657e13097de36daa5d8","observation_id":"7667d4a2-b706-4c5d-ae37-845e176a58c4","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Handling missing modalities in multimodal survival prediction for non-small cell lung cancer,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:ec4e7987c9850d6c36b8e470b4f4bf1864a37ac51006eed34692f937f12dd0bd","observation_id":"464c97d9-6a22-4ca0-8398-cae3f7e6979e","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Memory- augmented incomplete multimodal survival prediction via cross-slide and gene-attentive hypergraph learning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:eb0bd948f02cee6cf5c4f24e6de2c6e4dce0bfaf17cb9a4bbc12051cd2d50129","observation_id":"878342b3-86a6-4be2-8d6d-30f243dcad35","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"A machine learning ap- proach for multimodal data fusion for survival prediction in cancer patients,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:017402db9a1285d5f4855139c957ca35fb63d04a3bdcd0230b46541d207c5bd5","observation_id":"082c23ea-3250-445f-9826-72cc9e043bf6","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multimodal deep learning to predict prognosis in adult and pediatric brain tumors,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:a001f78b02bb7782c14b1f593194e720dab024c923ff64fb82adca1460239b74","observation_id":"60f48d61-1418-43d0-90e8-4c7e0ce1b534","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Foundation model-enabled multimodal deep learning for prognostic prediction in colorectal cancer with incomplete modalities: A multi- institutional retrospective study,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:0f67818e4ece356e3ef1a6214002c14cd51eaaf24acd6e498304b289841318d4","observation_id":"bcd4b459-7974-4090-9e2b-4e78b5dcce4d","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Long-term cancer survival prediction using multimodal deep learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:b3d9c2f043a760c9e408431f4d4fb91e4f456438482293db9bed2efa8cbc4e58","observation_id":"b0c3b85a-6d96-407f-a23c-9014b0180b0a","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multimodal data fusion: An overview of methods, challenges, and prospects,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:7218b97c2f1e6ebf36fc5729d9c0b0f308018f56acf6fb93c5072a978e350c2a","observation_id":"2956f9b0-bbac-4a93-af2b-2b5e22185245","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Artificial intelligence for multimodal data integration in oncology,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:002f4c0e332eb293547e690613704b52aeab88ce22ddfd150f11300c613dcddc","observation_id":"61a86d4e-1e9f-4c74-a4f3-f9255ec25e3d","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Tensor fusion network for multimodal sentiment analysis,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:23c51072331a390ce1340add0e87cb8e55793c7f44c6972df1df629760ffe08e","observation_id":"7422ff76-1178-4ae2-a374-abd8d97d5cf1","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Integrating multimodal information in large pretrained transformers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:405213745cc8609266a0b474ba892871c66c2053deedcacf9e31bc1b327ecdbb","observation_id":"a156defe-43c2-4164-9edd-d3d32ec977d3","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multimodal transformer for unaligned multimodal language sequences,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:5a58045f6a57de2975d1e4b0d9f3964058a8182c63307fcc1d2fd903803b2ca1","observation_id":"09fc84e1-c4ea-4afe-80dd-e27f4bc60d1a","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multimodal co-attention trans- former for survival prediction in gigapixel whole slide images,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:efda1e96c7935251a919273e1f605c8d785a3cf2d29c451589cdfb2fd02f71d3","observation_id":"a683141d-4f2d-4eee-ad39-44f9f22d3e71","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Pan-cancer integrative histology-genomic analysis via multimodal deep learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:43e1973554855383e0d3f8d2b029b2c3109b93e576f15464f37848de8216936f","observation_id":"d243a3b9-53f3-44ab-82ca-a2752348b322","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Pathology-and- genomics multimodal transformer for survival outcome prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:3f396403bc73c9d8173442534a7aa3d31407a33ee802fc06e40e98c0a3e00483","observation_id":"6487d3d2-4111-4a3f-a9ec-ebb3059a18d9","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Mul- timodal cancer modeling in the age of foundation model embeddings,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:318b52ef715489a66aaf1ce0550299a0b965939a759b7a603254d025cf77f9c4","observation_id":"7a22b112-57e4-42bc-b316-f926742561bc","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Towards a general- purpose foundation model for computational pathology,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:5439559b53208142fde22da8cc47735544f65477e0355f72ddc88eb16ebaf1a9","observation_id":"05acb375-b81d-4893-a8b0-780c64809749","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"A visual-language foundation model for computational pathology,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:76a89b8bb08b8834edc92fbff96839f73a4a99bdc52eb9bdd41aa2fd79f507f2","observation_id":"431f814f-0974-427c-8d14-49a36c0bee20","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"A multimodal foundation model to enhance generalizability and data efficiency for pan-cancer prognosis prediction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:2dbb9008c7843cd98c5eaad74c05441b38376b6917e6192adaed8aca99e2d12f","observation_id":"5980847e-8d25-4a14-8471-d0cbffd5ec7f","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"POMP: Pathology- omics multimodal pre-training framework for cancer survival predic- tion,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:7f29d4af2ad522dc19368cda981c119733462b6ea7dec992b718d345b89eba33","observation_id":"cd9d919e-2690-475d-b334-64bec2cc9748","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Robust multimodal survival prediction with conditional latent differentiation variational AutoEncoder,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:232c661c7e104eda4c69870f986603ae8e8b85c02633ac4b8e5af7134465abc4","observation_id":"550a32ed-2ea1-41b2-85e7-95e716b3b221","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"M3AE: Multimodal representation learning for brain tumor segmentation with missing modalities,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:2d44f0101257fd59ff7245a11b12103e3d39cea50fc6f7ec0c78e739410d0b54","observation_id":"5e6b6eb4-fa00-497b-a1f3-1126d8bbb7b1","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Multimodal masked autoencoder pre-training for 3D MRI-based brain tumor analysis with missing modalities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:81abcd2f620c09c0a6a08bcab9f2e2e827be96e3e4176e4523aa8364551fd71c","observation_id":"b8ee6611-66a6-48fc-b8b2-c624a4bc06fb","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Closing the gap in the clinical adoption of computational pathology: a standardized, open-source framework to integrate deep-learning models into the laboratory information system,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:ff9161acd2b3c117fb3736528e058ceb86ad9135137e5eed1423553ed565b392","observation_id":"30397821-9d3e-472f-abaa-bcb48983badf","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:1e11e7ab4e0661f560fd39da80ffe1e901248082f8221d14acbe0cb7b19e19c7","observation_id":"2b1f6231-b9b1-46cf-97f5-949deabeecb6","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"BulkRNABert: Cancer prognosis from bulk RNA-seq based language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:d6801c0ffc6f81f36f23be50253217e363c07329efb534e431d49907163b369f","observation_id":"1008d26f-d8c2-404d-8299-d8194fd64c90","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Publicly available clinical BERT embeddings,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:e2e6caeff60f44ed89702b79d0f2eb5cb0a03fc8a66b1ad40c0dd329fee1b4d8","observation_id":"dd742c68-2baf-4b19-aaa4-badfc8aa4aa0","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Attention-based deep multiple instance learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:63c61a0c8a9fd09bbac278f1d7b95c1abafc72e778a66d044f9557f35eb6a749","observation_id":"79e1c782-37ec-42a2-9be7-099a26ddc725","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Self- normalizing neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:1407a5b8635c0031444c82e77cfd5978ca71dfe83e558dcd0c46db7783f45f95","observation_id":"dcf4f787-1acd-429b-9196-a5c84026946c","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T10:21:01.818157Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-13T10:21:01.818157Z"},"links":{"citing_paper":"/paper/2604.04999"},"observation_digest":"sha256:0e91484e392d24094043050133bebbcc2cb1377d729c3042651964c212f3433b","observation_id":"3b981156-d3c3-4613-81a7-00c80ae5f6dc","resolution":{"observed_at":"2026-07-13T10:21:01.818157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2604.04999","last_updated":"2026-04-05T21:14:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T08:02:38.526940Z","submitted_at":"2026-04-05T21:14:27Z","title":"PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":36},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2604.04999."}