{"as_of":"2026-08-23T14:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5c52dcbce75fd0eb404833579f3d339d8093a7178cd55e9bce65e08911404fba","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-09T21:07:05.535810Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2604.22061/citation-record","integrity":"/paper/2604.22061/integrity","json":"/paper/2604.22061/citation-record.json","paper":"/paper/2604.22061"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3a38fae8-dc19-43a3-97b0-34e00ecb9378","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:4ca05ce927b5c9c184feb89ea2ae9ba47a0dad3ac13596ad343e51357cc9a830","observation_id":"39b4975b-50ce-41ff-8876-3f6445bbd21a","resolution":{"observed_at":"2026-05-23T16:23:12.796133Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"Settings","venue":null,"work_id":"7cd0b9bb-21b2-497e-a9a9-3df95240b63f","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:3458f8559be1c6690bc0d7f66b48576a721a67d8325573774251858eda33b83d","observation_id":"1e06dabe-557e-45e2-87b6-500a5e77cf70","resolution":{"observed_at":"2026-05-23T16:23:12.790984Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"MET” or “NOT MET","venue":null,"work_id":"f7a8511e-0574-4c9c-8faf-12784fa74cf0","year":2016},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:5b2167b3367090041b0d0c25883d946b7c1672a6353afcf752850755628a0e75","observation_id":"56ee2799-275a-4b11-8f56-3efcbdd67305","resolution":{"observed_at":"2026-05-23T16:23:12.705520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"Our primary evaluation focuses on precision, recall, and Macro-F1 scores for the binary classification task of determining whether a patient meets each of the eligibility criteria","venue":null,"work_id":"9f7571a3-3ea3-4f7f-9f67-12fbcd6d5a77","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:6d5f15ba6a7c5b3e06330be420f4a3a437ac9be8635189b8af061ea6e1bfae1b","observation_id":"0b6c908f-4cc8-4007-bb36-67625f9b4cc0","resolution":{"observed_at":"2026-05-23T16:23:12.716745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"As shown in Figure 1, substantial performance differences arise solely from variations in how the shared representation is processed and classified","venue":null,"work_id":"5688269b-be81-4ae7-9dd1-d2b8ec2ec1a9","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:82a2ded0ad62f78da0343dfd6d4c2e63ebb145bfd37192d521355a7b0fabbabe","observation_id":"97c35cef-d898-483d-9534-011d927e1d00","resolution":{"observed_at":"2026-05-23T16:23:12.767748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"Figure 2 summarizes performance across structured-only, unstructured-only, and mixed EHR settings using Macro-F1, AUROC, and AUPRC","venue":null,"work_id":"f0d37d22-1226-46e6-997f-a1d054ec7daf","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:4d265630717330333a02348a2a747080003432cd2d41ec4b9e9a5be832e59895","observation_id":"531ff527-cd94-4fda-8ceb-428f9d56bc0a","resolution":{"observed_at":"2026-05-23T16:23:12.773458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6900.6760","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c621be9a-615a-41ac-a59e-a62b072374fb","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:05b66eeb383073e5f8a64d6f8a8102056ef2eed0213a7da13eb8b65eade1c2c5","observation_id":"f524f3d5-ebcd-4097-8889-be8712f35d68","resolution":{"observed_at":"2026-05-11T14:46:23.065682Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"4ee381f4-fb4d-4391-916b-22cff19304d7","year":2021},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:a470c856ba8fba38b2aef77b4c05db26768a94b5ebfb9b9d0b73fac165f1f4c8","observation_id":"a81c469f-0ad5-4803-b2b5-f23e479f551f","resolution":{"observed_at":"2026-05-23T16:23:12.757883Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"As shown in Figure 5, clear performance differences are observed across model variants and evaluation settings","venue":null,"work_id":"049e92ed-16e2-4e0a-aa64-6c8a2de41bbc","year":2016},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:120bb98b178fe116a316239372b9b89f09317c1d703f60254ec71471ef10587f","observation_id":"dc3fa66b-4b26-4ad1-a488-9b55930ec228","resolution":{"observed_at":"2026-05-23T16:23:12.779991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"21b20e82-8511-442e-a2eb-b21ea5c882ae","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:fecafb8ffe8e17dfeffb5e60f51b0b6f0971f43d9d3bbc5bbea64952d43b640b","observation_id":"4ee108fa-8dec-4633-bec4-c7ff5d4fcc4c","resolution":{"observed_at":"2026-05-23T16:23:12.726107Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2c167b50-538c-444a-9859-b73ab639b750","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:add621fe2c42818d6e2a3dbf9c3ed8fe734c6bc1d3aabc500e80c4895a016456","observation_id":"29f13e7e-b302-400e-9e3c-4d1af1a74d02","resolution":{"observed_at":"2026-05-23T16:23:12.711208Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"potential/eligible","venue":null,"work_id":"3f131e09-b188-416b-a35f-ae354628f60e","year":2021},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:48419f14661cbafe76008631f1809c36b2dd5c5fd5ccb3b1ae90b0f68da053f5","observation_id":"c6790446-86c1-44fb-baa8-cd710e1e8a39","resolution":{"observed_at":"2026-05-23T16:23:12.735829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"66fd2f14-5094-494e-b826-157bc401377b","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:12a1b2d7e61dc528d844ff63ee6c249a4b013ff84230847312db71c7d7b82275","observation_id":"d2daf48a-071e-4329-8e13-2687d14fa74b","resolution":{"observed_at":"2026-05-23T16:23:12.761704Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9b89ce41-46e4-482b-ae88-90d1eafa3a48","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:701e6baa944eae6d574a6496e9a98fcc19b62fa3a29996ebe385910e3071c13e","observation_id":"9f662348-8ad7-4905-9833-74b6c77cd73d","resolution":{"observed_at":"2026-05-23T16:23:12.745441Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"RAG-encoded inputs were fed into each frozen LLM, and the resulting embeddings were passed to the same MLP classifier","venue":null,"work_id":"c73976c9-9631-41d9-8cbc-5af6ab9354b3","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:5c07eee11fa68bb6f9f72407cbfee8b2a8cd28917b50d6a093c4ef8455de13cf","observation_id":"1d4d91ac-023f-4db9-b48c-64cd6e499720","resolution":{"observed_at":"2026-05-23T16:23:12.752814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a54fccb7-b3e1-4a15-9842-e8b016a0f17d","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:15e0941b59d40f353defbf34d0ff4e942fe47b17f738b3402ebd6314843d1fbd","observation_id":"7ad2adbd-2b35-49fa-a02d-d4b0d8d62800","resolution":{"observed_at":"2026-05-23T16:23:12.729804Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"Frozen (Task 4) To evaluate the benefit of representation adaptation, we compared frozen and fine-tuned LLM representations within identical RAG-based pipelines","venue":null,"work_id":"7d0a48d0-8cf2-4395-bfd8-bd344a3d45d8","year":null},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:0b762cf5a6b79f14bd6910e8cf80b42f859ca99b1ad7e2d6a3c961dbff374d72","observation_id":"34f15fd2-4fa1-4ec9-b84c-7d7452b8caac","resolution":{"observed_at":"2026-05-23T16:23:12.785207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"Performance was compared against zero-shot methods and TrialGPT using the evaluation metrics reported in the original studies","venue":null,"work_id":"bc6ab21d-16cd-4ea0-92e1-a50a991f5446","year":2016},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:65a340bb1859930f3df04f02ec2e36b6c97f62cbb92b0837ed27cd82267bbed3","observation_id":"21edbf21-dc3f-4bae-9e34-ec8425163cd1","resolution":{"observed_at":"2026-05-23T16:23:12.721300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"All experiments were performed using the mixed-data setting","venue":null,"work_id":"08df6f92-c7f2-41b9-b09e-1ad661dd6254","year":2021},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:0f10b3fee367575ad63a7af6f6117114ef62c5b48000dabaf3ce611bf16a1eb8","observation_id":"73be378f-e772-4949-b750-e33d12563e9c","resolution":{"observed_at":"2026-05-23T16:23:12.741048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-05T21:23:00.469572Z","title":"EliIE: An open-source information extraction system for clinical trial eligibility criteria","venue":null,"work_id":"7d1ff60e-741b-47dd-94d5-5454542fef70","year":2017},"citing_paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:05.535810Z"},"links":{"citing_paper":"/paper/2604.22061"},"observation_digest":"sha256:42fdd72fc35b57fbc280874874a9d109642f3082f1f66a8d968d5accb0fdc33c","observation_id":"0df12fac-fb4e-47e4-9ae8-8d024c8ff39f","resolution":{"observed_at":"2026-05-23T16:23:12.801587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.22061","last_updated":"2026-04-23T20:36:38Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-23T20:36:38Z","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":7,"verified_exact":1,"verified_fuzzy":11},"total_outbound_references":20},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2604.22061."}