{"as_of":"2026-08-21T12:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7512d0e38db42a5cf906accc1eda6ff63891ece4a6b9fb5bbc48c15a6d5198d0","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:28:42.323193Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2505.12848/citation-record","integrity":"/paper/2505.12848/integrity","json":"/paper/2505.12848/citation-record.json","paper":"/paper/2505.12848"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:28:45.102557Z","title":"Innovation in the pharmaceutical industry: New estimates of r&d costs,","venue":null,"work_id":"f53f168d-e9e3-409f-a2ce-a2f46c362709","year":2016},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.680083Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:21588b3c0922ddb784f3f9b1cae279b11cd02d813c8ae03d857fc735b3a82d1c","observation_id":"5e7a8a08-167d-4244-8824-9244ceec49d5","resolution":{"observed_at":"2026-08-15T20:28:45.106527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.989074Z","title":"An analysis of the attrition of drug candidates from four major pharmaceutical companies,","venue":null,"work_id":"a9827831-370a-4c67-8d94-66fc42ccb36c","year":2015},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.684516Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:afd60fa589b547e32f22466cf720c81be30d4966bf9789dea14ad380ac8ce3e4","observation_id":"7b4cbb2b-f021-4dde-a5b0-d958651549e6","resolution":{"observed_at":"2026-08-15T20:28:45.046543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.977650Z","title":"2015 fda drug approvals,","venue":null,"work_id":"202bf658-0ff7-4325-9bbc-081ea53b6121","year":2015},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.689323Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:d84acbc5ebd894b84a2f6bc5f7757da202eee3a41c179daa702a01cffb545baa","observation_id":"d28bb12d-9f85-445b-91ca-003be6a0a55c","resolution":{"observed_at":"2026-08-15T20:28:44.981205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.965238Z","title":"Estimation of the size of drug-like chemical space based on gdb -17 data,","venue":null,"work_id":"83710486-07b8-49ea-b267-687cfe18e4f2","year":2013},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.694491Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:a6168fecaa9b13132625c00d5469cb7ff5f069bd7c249bc0ea53cbe254ce2ace","observation_id":"a4b9fd00-51c8-4865-be70-a327bb6f0f90","resolution":{"observed_at":"2026-08-15T20:28:44.969673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.925786Z","title":"Rethinking drug design in the artificial intelligence era,","venue":null,"work_id":"576d1654-7b63-4e40-89a3-5572b8ca23c1","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.698981Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:df1bb9451b403ba292f6ed05b951e7475eb40ae19e5b9e4a4801176cfd914dfd","observation_id":"1b2a6520-5f4c-4fb5-bf5f-68f13cc0e09f","resolution":{"observed_at":"2026-08-15T20:28:44.956574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.735430Z","title":"Applications of machine learning in drug discovery and development,","venue":null,"work_id":"51d24102-0841-4ca6-9fa3-740953dcaf4e","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.703092Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:188696468286fb9efe8eb21cd4b492c5b105ea9064c16c67d57a8f01bcdd6e37","observation_id":"e06d4b04-df63-43bd-bdb4-a32d5b5d89a3","resolution":{"observed_at":"2026-08-15T20:28:44.800582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.647502Z","title":"The rise of deep learning in drug discovery,","venue":null,"work_id":"77b6d5fd-eeec-438d-ae6f-bbb5569c283a","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.707764Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:ef4402fe9dc29ad1d22af84fe7f5ed6418f2a213e17526e7677cecaacdb68e95","observation_id":"0374f991-d824-42b2-84e2-ee9b7f99965d","resolution":{"observed_at":"2026-08-15T20:28:44.651736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.635892Z","title":"Deep learning for molecular design —a review of the state of the art,","venue":null,"work_id":"f4e2ded2-17a1-42ac-8db7-36c3fb02bb29","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.711143Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:59d01028c588f8ab0d28d1edc6d37cd1bda8869df19ee8a91a1491c0a2ef798c","observation_id":"7fee03df-ff2b-442b-b612-84181eef5422","resolution":{"observed_at":"2026-08-15T20:28:44.639591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.623522Z","title":"The´ power of deep learning to ligand -based novel drug discovery,","venue":null,"work_id":"e0d5c940-f711-47a9-9ca4-d207abd02944","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.715047Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:3a3ead739a6a3ea0f7c8eb3147215a0ec398d92ff8fba58d1be28a116f13c0f4","observation_id":"be2ad2cb-fc94-4d88-b92d-f48a4c1d0ded","resolution":{"observed_at":"2026-08-15T20:28:44.627871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.393373Z","title":"Inverse molecular design using machine learning: Generative models for matter engineering,","venue":null,"work_id":"08eef00e-13e9-4e50-b4ac-49afae5ec00b","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.718716Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:bce7cd7436245a48c87fda6602e45d6580a4173acd3fc5433882ef442c74a562","observation_id":"81442873-5426-4995-b19b-80e08507783e","resolution":{"observed_at":"2026-08-15T20:28:44.455831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.379436Z","title":"Applications of deep learning in molecule generation and molecular property prediction,","venue":null,"work_id":"04f43511-a6d5-48bd-94c6-cf904968571a","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.722151Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:2f94638e0857925ef0f4c378d6c343ff3b51cb138850404498e24ae9cf0bef33","observation_id":"759a3d54-7d38-4e6f-8d1c-9f22c3683d27","resolution":{"observed_at":"2026-08-15T20:28:44.384500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.333953Z","title":"A deep learning approach to antibiotic discovery,","venue":null,"work_id":"89925528-49a6-474d-a7dc-8ff2e170aee0","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.727536Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:0e9574c3458b8667020569f6cd1393aea2010186ef360e89d0d70f0042261087","observation_id":"eb1f4c25-cc3c-49c3-843b-7abd40ff5e36","resolution":{"observed_at":"2026-08-15T20:28:44.370217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.137254Z","title":"Deep learning enables rapid identification of potent ddr1 kinase inhibitors,","venue":null,"work_id":"e89a9fb6-72e4-49e4-bdfb-0978d656ee0b","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.731443Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:b792a830c2759fc39235599c5c2e2c7de02cc37e05988ebf678b7af7ab129523","observation_id":"2e85bf34-b0d1-43c5-9b7f-66d759a77146","resolution":{"observed_at":"2026-08-15T20:28:44.229101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.077371Z","title":"Guacamol: Benchmarking models for de novo molecular design,","venue":null,"work_id":"ce29433e-a383-450f-8a07-dc738506bfeb","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.734892Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:8cac2ec6b188e58fe5f9bbb01a7abc2678cf23458cb859e2bd37dfd07e4bbc98","observation_id":"fd5cea95-ac06-4d64-8423-78e8c827b739","resolution":{"observed_at":"2026-08-15T20:28:44.081478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.063025Z","title":"De novo molecular design and generative models,","venue":null,"work_id":"19d6cc51-002b-456f-b12a-c34e951b595d","year":2021},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.738386Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:b5396616d81d6606bdef74e430e9d8a54a8902be95403e7ee091b99de37ffb6f","observation_id":"b6d4a8c6-c270-4b64-a2e6-0e36e9d94205","resolution":{"observed_at":"2026-08-15T20:28:44.067944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.051072Z","title":"Molecular Sets (MOSES): A B enchmarking Platform for Molecular Generation Models,","venue":null,"work_id":"d1ee6940-c1ae-4cc4-9672-b0cdefb4aefe","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.742104Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:9a39297fd67fc74fa3bc86f650b5624f1b28858f1db0bb3a13bec3a3fdbb0d6b","observation_id":"922fb9c7-0ed2-423e-83e6-4b401c584c43","resolution":{"observed_at":"2026-08-15T20:28:44.055710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:44.039050Z","title":"A practical overview of quantitative structure-activity relationship,","venue":null,"work_id":"49c3ef02-6a15-45ee-a33b-d8d2806a332a","year":2010},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.745773Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:1eec37c276120cd9d6f12dc40ad28e4398a06deb67259107bc97025b670dc952","observation_id":"51f32fca-2d84-4000-8675-e043caa8082e","resolution":{"observed_at":"2026-08-15T20:28:44.043340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.843949Z","title":"Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules,","venue":null,"work_id":"dafeb4f0-e3d4-425a-8a1b-1885aeff4acd","year":1988},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.749858Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:3ff64e5789a86d2d4a68ce0a9c0257c41f16559f069e183b13e8640fb026d815","observation_id":"674bdfdf-3fb9-499b-91e1-26b5ead48e12","resolution":{"observed_at":"2026-08-15T20:28:43.938546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.724804Z","title":"Convolutional networks on graphs for learning molecular fingerprints,","venue":null,"work_id":"db2f2067-c4b1-4100-8531-621a962d242a","year":2015},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.753804Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:c5735a21415d2d145d5d9643441d52cf3db4db19e313e049c83afcfba57c27cf","observation_id":"6a2e4466-dec4-452a-ac6a-b8550cbc710f","resolution":{"observed_at":"2026-08-15T20:28:43.729184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:41.757770Z","title":"Extended-connectivity fingerprints,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.757770Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:e42a7894e5dfb362223f028b468bada20f65d9ce4236aff3100abb219e1ddeb0","observation_id":"df85e3c9-3f34-4ed7-bbaa-80cd3276460a","resolution":{"observed_at":"2026-08-15T20:28:41.757770Z","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":"2026-08-15T20:28:43.702536Z","title":"3d molecular representations based on the wave transform for convolutional neural networks,","venue":null,"work_id":"275102ba-018f-4adc-81c0-c3ef8d6bf14d","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.761344Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:aab4dbfc13ec368b812dbb549ce2637836994eebcd8cac73ebc9d11bce3199a5","observation_id":"11075e06-15f5-4c4d-ac88-e069eea8ce3e","resolution":{"observed_at":"2026-08-15T20:28:43.707386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.666961Z","title":"Generating focused molecule libraries for drug discovery with recurrent neural networks,","venue":null,"work_id":"c9479db7-52aa-4879-93e8-44980ca7e572","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.765181Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:413fb0aa9587d3fb81ec88a9bab8b8f694803deeb3e77500b6b05173b69320ec","observation_id":"8aebe252-53e0-4b51-89d6-01a671f4e195","resolution":{"observed_at":"2026-08-15T20:28:43.670956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.654198Z","title":"Generative recurrent networks for de novo drug design,","venue":null,"work_id":"4ce5478b-2a70-410c-af15-1d6410831d2e","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.769814Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:da3e1ca66a7e2894ca2333f9720b76f0731ef9fa61dad821483c3afb8a83c48a","observation_id":"bd6238f2-cc43-4979-b5a4-ab6ca67ffbd1","resolution":{"observed_at":"2026-08-15T20:28:43.659374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.640675Z","title":"Automatic chemical design using a data-driven continuous representation of molecules,","venue":null,"work_id":"f187b25f-e4ee-4d68-99bf-6157f71fe029","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.774003Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:4789cfa884207298a2b04a0b03ed822cba223d8c9c5a8742fb90f56a020e4588","observation_id":"ec10baf6-9aa4-4573-9009-62f477643f10","resolution":{"observed_at":"2026-08-15T20:28:43.644971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-15T20:28:41.778242Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.778242Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:07e0beea866148c40d074e06a31fadc35a3711443fdd14aa6459ca4ce98de16c","observation_id":"4b35148a-722a-4a5c-b2eb-33c1424f3892","resolution":{"observed_at":"2026-08-15T20:28:41.778242Z","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":"2026-08-15T20:28:43.628611Z","title":"De novo design of new chemical entities with reinvent,","venue":null,"work_id":"2a89cee6-2d76-493b-b2cf-f8cad22c38f5","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.782517Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:31ac8bbfd6b830f1ccd00dcc47d15ebe7b8274f53424e76c426fb188888a32f5","observation_id":"3750a654-5717-4b92-b4d0-ad3338712a48","resolution":{"observed_at":"2026-08-15T20:28:43.632852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.615156Z","title":"A de novo molecular generation method using latent vector based generative adversarial network,","venue":null,"work_id":"f1728c76-257a-4fb0-8c52-21808b34ecc5","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.786520Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:a16f13bcddf4bc464ed317ff80eeef07e3d87956a94e528928bbbf85990ed359","observation_id":"18ec0ab3-5693-4708-86a9-48bd7b056b01","resolution":{"observed_at":"2026-08-15T20:28:43.619752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.413477Z","title":"Generative adversarial nets,","venue":null,"work_id":"20dcaa1c-9421-4212-b6f4-b53753965b16","year":2014},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.831794Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:c35dd4773e6c975c2d2f7a497af195489269231793f914bb8e5cab8b3f4b791e","observation_id":"3ccb5a47-ca54-45c5-8752-aca1f6542c0e","resolution":{"observed_at":"2026-08-15T20:28:43.543857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11600","last_updated":"2019-05-28T04:13:23Z","snapshot_observed_at":"2026-08-14T16:25:29.394963Z","submitted_at":"2019-05-28T04:13:23Z","title":"GraphNVP: An Invertible Flow Model for Generating Molecular Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11600","snapshot_observed_at":"2026-08-15T20:28:41.919455Z","title":"Graphnvp: An invertible flow model for generating molecular graphs,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.919455Z"},"links":{"cited_paper":"/paper/1905.11600","citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:752c2e1f17458c450bf2d3d55cd1cad7265b09e7daeb9e25164c51df21262a60","observation_id":"2ff10e62-5dcb-4610-b653-dd9eda06f86c","resolution":{"observed_at":"2026-08-15T20:28:41.919455Z","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":"2026-08-15T20:28:41.946867Z","title":"Mermaid: Metaphors for molecular generation,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.946867Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:8251d11a0102680490e3a5d85e84b054941c123b6fa95ab9266f90603481cebd","observation_id":"3d331c9b-1584-4010-aa8e-22d511926888","resolution":{"observed_at":"2026-08-15T20:28:41.946867Z","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":"2026-08-15T20:28:43.361813Z","title":"Molecular denovo design through deep reinforcement learning,","venue":null,"work_id":"074f8fb5-d43d-4896-bfff-ed46472ed9aa","year":2017},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.973910Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:10ea4538c497bd7086630400fa54d753df8a629ad86cda876724aeb7353388e8","observation_id":"bea82614-6a22-4ff6-baa4-35db842dcc76","resolution":{"observed_at":"2026-08-15T20:28:43.365995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:41.978481Z","title":"Deep reinforcement learning for de novo drug design,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.978481Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:4397f0011dc1230b2240a19fc3760ac63db64e1850f2b6f44f14e22c95efe255","observation_id":"33875457-53b5-4973-95ad-f5e6b4c25d6c","resolution":{"observed_at":"2026-08-15T20:28:41.978481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.04738","last_updated":"2019-11-12T08:44:49Z","snapshot_observed_at":"2026-08-21T11:51:13.364780Z","submitted_at":"2019-11-12T08:44:49Z","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.04738","snapshot_observed_at":"2026-08-15T20:28:41.982376Z","title":"Smiles transformer: Pre -trained molecular fingerprint for low data drug discovery,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.982376Z"},"links":{"cited_paper":"/paper/1911.04738","citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:f0c501614540e371ccb9aea62b621fe73d3d599e7d037b031ca10a6e6107efe8","observation_id":"cf9ac61a-8077-4de2-b6e8-6f20ce7e6957","resolution":{"observed_at":"2026-08-15T20:28:41.982376Z","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":"2026-08-15T20:28:43.340923Z","title":"Mol - cyclegan: a generative model for molecular optimization,","venue":null,"work_id":"edf583b8-d8a1-4d11-bb25-9a5bb102be25","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.986188Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:a546dfb5d499d7ae85dc084bf87ef0379c42e522e7709d0fd83d5744f6cc74a0","observation_id":"9de11df0-e038-4d08-844c-73a830065dfd","resolution":{"observed_at":"2026-08-15T20:28:43.344955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.329231Z","title":"The molecular transformer for organic reaction prediction and symbolic inference,","venue":null,"work_id":"3a15455b-bf6c-49de-9dd0-dd3712fc151b","year":2022},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.990387Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:4fb349c84eeec9e9ea603128ab582c26125c90413a99dad5c7f0830445feabc8","observation_id":"7538318c-e87d-4630-ae8a-f11278382e2d","resolution":{"observed_at":"2026-08-15T20:28:43.333784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.260442Z","title":"Frechet chemnet distance: A metric for generative models for molecules´ in drug discovery,","venue":null,"work_id":"14c86dee-acf8-46ed-8e37-5874afcc4387","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.993926Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:bb0c4bf0f46273f529cb6343b75378c895f52a94501a18fc8bd734e8b9cbaf34","observation_id":"bdeff399-01e7-4088-bff9-4f14c0c7f47c","resolution":{"observed_at":"2026-08-15T20:28:43.320698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.127193Z","title":"Estimation of synthetic accessibility score of drug -like molecules based on molecular complexity and fragment contributions,","venue":null,"work_id":"814a2759-7dd6-4a0b-b034-14aa22c0a149","year":2009},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:41.997797Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:e8e37120577bb094149d9cdfcf02a388db83a476f7c42ff830e9aa4c34507ef8","observation_id":"4baa31f8-1479-4982-a596-c7aaa3901c0b","resolution":{"observed_at":"2026-08-15T20:28:43.182545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.069288Z","title":"Zinc 15–ligand discovery for everyone,","venue":null,"work_id":"78c57c2c-3f7f-4a52-b8c8-6858bb5fff7b","year":2015},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.001133Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:88e5acaf49b49a1c6b2d707c8553ceef78e6e7e8c55918c8529751fab5025d88","observation_id":"51c97b76-4db7-4c11-882c-87cc741348b9","resolution":{"observed_at":"2026-08-15T20:28:43.083820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.057858Z","title":"The pains problem in virtual screening,","venue":null,"work_id":"e41a2cb0-dfd8-4733-832f-c9bccfa61fe5","year":2010},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.005322Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:1a1e2968584948cd4d8fb0c654b71bd184b75cee3a7496667c4ad5ed23e9194e","observation_id":"4e65ef1d-1c0a-435c-a58a-68e1ed595b85","resolution":{"observed_at":"2026-08-15T20:28:43.061647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.047092Z","title":"The properties of known drugs. 1. molecular frameworks,","venue":null,"work_id":"b2c5ce79-3ff7-4c33-a2e0-8c69eebbad2a","year":1996},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.009651Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:7d94fc3787be1d7d642ec4bd793b84b9d5d1d983a6f5687d3ad5796b807d6348","observation_id":"6582c06a-e11e-4316-a2e8-aa8d60875fe1","resolution":{"observed_at":"2026-08-15T20:28:43.050825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.035904Z","title":"Junction tree variational autoencoder for molecular graph generation,","venue":null,"work_id":"783e76dc-2ee5-4a26-8448-59019aebafa0","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.014021Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:144fde110f3913032762aeaf52c32715ea219859532957d7811bc009ad7f94bb","observation_id":"c5b492e8-c7ad-4a42-821a-0cb60220f9b3","resolution":{"observed_at":"2026-08-15T20:28:43.039987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.023908Z","title":"Prediction of physicochemical parameters by atomic contributions,","venue":null,"work_id":"ecfea386-3059-4a66-b4b4-857f1e7c1106","year":1999},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.018255Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:87b49a3c7df71aa65746979512c95a4c4c0252c5ba73f1bdc47489285ee2b0a2","observation_id":"606e929a-7a95-44d5-97b5-71c12ee6fa43","resolution":{"observed_at":"2026-08-15T20:28:43.028117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:43.011069Z","title":"Quantifying the chemical beauty of drugs,","venue":null,"work_id":"228859ad-d64b-48ff-9ab1-5ea00713185b","year":2012},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.023101Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:d653bf4e396065a01c9baa941ecb8b55408565c3224a145df6686f21b148d886","observation_id":"84e86dc0-2a14-473e-85e1-f01f8c623f7c","resolution":{"observed_at":"2026-08-15T20:28:43.015366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.998398Z","title":"Randomized smiles strings improve the quality of molecular generative models,","venue":null,"work_id":"22dc1939-3f15-4166-bb41-bb8dfbb471ab","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.027405Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:ae89eb23367f2da0c119ad998ed77936597d5c931ead5d13d7f4c51b37b8b08d","observation_id":"532ca8e3-3a9d-4d43-bd04-2158c910b65c","resolution":{"observed_at":"2026-08-15T20:28:43.002458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.931512Z","title":"Learning con-´ tinuous and data-driven molecular descriptors by translating equivalent chemical representations,","venue":null,"work_id":"3480ee61-892e-4730-bd33-24c32c84f14d","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.031637Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:af191ba0dae266466f7d47429adde13ce7536497d3eedaeb560c2f992cd660b2","observation_id":"13592c14-e588-4b86-b582-e955fd8ed08a","resolution":{"observed_at":"2026-08-15T20:28:42.990475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.816083Z","title":"Application of generative autoencoder in de novo molecular design,","venue":null,"work_id":"798835d0-bae3-434b-a082-28cb3b1ac30a","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.036097Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:e6665c3ae2ec18cde565baf718c03e5ef3423754d4a5c1d4aa29851de853f492","observation_id":"8856d147-8b12-4085-84b8-0511200d8dce","resolution":{"observed_at":"2026-08-15T20:28:42.820217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.803975Z","title":"Generative models for molecular discovery: Recent advances and challenges,","venue":null,"work_id":"3db1b24f-9d19-4c83-ba83-06febecdb6bf","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.040373Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:bd60f9eaf0d88eed39d2e51a795d0bae2f1bb0ed2793fc384509547084e5206d","observation_id":"23851463-72f9-4a2b-8d3c-0dacc67ca992","resolution":{"observed_at":"2026-08-15T20:28:42.808007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.792083Z","title":"Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems,","venue":null,"work_id":"e85ba0ea-5be3-403f-b55e-3690432eed08","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.045752Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:abab9534c3fee66d9ad07623e69cced23928d5765d5cf3730a2b1cf1df9177db","observation_id":"f3e4ebe1-8963-42f3-998c-d23a6f7dbfb1","resolution":{"observed_at":"2026-08-15T20:28:42.796051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.780236Z","title":"Population-based de novo molecule generation, using grammatical evolution,","venue":null,"work_id":"78809439-e1d3-4293-b8af-eba8e0207682","year":2019},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.050192Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:3f007bb424e20523dac2f19d512cb19b28ac6d6b6f81ec92ab3bcefb5e032718","observation_id":"1d1e4c1f-952d-4a09-94fb-8a1d1731ee05","resolution":{"observed_at":"2026-08-15T20:28:42.784443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.760957Z","title":"Autonomous discovery in the chemical sciences part i: Progress,","venue":null,"work_id":"0271ab24-637e-4d90-9473-e91d167ae400","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.054361Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:761f8d91c18f6b6ea613ec125f3c16412d773be186acb04ffa5d6ddb6a7c33fa","observation_id":"70432713-27a8-4bff-b08e-7fce1ade71cf","resolution":{"observed_at":"2026-08-15T20:28:42.772851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.597460Z","title":"Deep learning for drug design: an artificial intelligence paradigm for drug discovery in the big data era,","venue":null,"work_id":"bc79b98b-b38e-4272-b18c-1de57e26c629","year":2021},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.058398Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:55a93fae57d1ff26171c95ee7f4dbbe222628db2e064c545e7af4527fd81c023","observation_id":"4e93eee7-d37f-465f-9224-1715aa95c29e","resolution":{"observed_at":"2026-08-15T20:28:42.648472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.561350Z","title":"Recent applications of machine learning in drug discovery,","venue":null,"work_id":"7e167599-8964-4c6e-ab2a-aecd4ee772c0","year":2018},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.102291Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:3fe17e4ea24ae128659e172e8066447057b933f6d52f3f31c8444f4b6b9cbdcb","observation_id":"fe1a29bd-1d64-4f08-8159-676d6b318376","resolution":{"observed_at":"2026-08-15T20:28:42.565359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.547791Z","title":"A practical guide to molecular generative models,","venue":null,"work_id":"9999a113-f3b8-4cfb-b7a8-87a33ffaccaa","year":2022},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.178669Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:0743e289a87231800b914c6a6e5955677aeebe05497fddd2c5fa51b47897f8bd","observation_id":"9cfcf617-3f10-4cbb-a37b-649bfb13521a","resolution":{"observed_at":"2026-08-15T20:28:42.551670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.534468Z","title":"Exploration strategies for discovery of interacting multi-target drugs,","venue":null,"work_id":"d5ff1173-fbf0-4b8c-afad-8347fc2571ce","year":2020},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.238727Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:11165dd688a8fed47ffe0c5fc9ec70825df2b1edcc6afe032e4b10f6215d45d0","observation_id":"983472b9-c477-4c63-8a87-5c8cb3ed9d2b","resolution":{"observed_at":"2026-08-15T20:28:42.538968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.519150Z","title":"Artificial intelligence in drug discovery,","venue":null,"work_id":"80b8bef9-47a4-4767-9ed0-39d0d1f0d4d3","year":2025},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.315849Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:a93ac32c139523572726a5d68faa574a54236948f5f476e8995eb54ae2b6aaab","observation_id":"5abe700d-af4c-433e-a9c5-518bbb5880c2","resolution":{"observed_at":"2026-08-15T20:28:42.523342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T20:28:42.503307Z","title":"Molgpt: Molecular generation using a transformer -decoder model,","venue":null,"work_id":"c4630d2d-c12a-4bd5-a954-86d2c0b2c08c","year":2022},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.319975Z"},"links":{"citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:3f8add34db29759822f7b04b7c3832124d75106d1e72a6a6f26a610a2834843c","observation_id":"104c7070-b58f-46fb-8859-ea612923821c","resolution":{"observed_at":"2026-08-15T20:28:42.509215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.01776","last_updated":"2023-02-11T17:58:30Z","snapshot_observed_at":"2026-08-17T12:35:59.585149Z","submitted_at":"2022-10-04T17:38:14Z","title":"DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.01776","snapshot_observed_at":"2026-08-15T20:28:42.323193Z","title":"Diffdock:¨ Diffusion steps, twists, and turns for molecular docking,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:28:42.323193Z"},"links":{"cited_paper":"/paper/2210.01776","citing_paper":"/paper/2505.12848"},"observation_digest":"sha256:a11d63fb44982f1fa50393ae7508cb80df07f05d604c327904b255a60b2e496e","observation_id":"0a083448-adcc-435f-9165-ad93f2904bdd","resolution":{"observed_at":"2026-08-15T20:28:42.323193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.12848","last_updated":"2025-05-19T08:34:38Z","latest_version":1,"primary_category":"physics.atom-ph","snapshot_observed_at":"2026-08-20T05:52:40.962906Z","submitted_at":"2025-05-19T08:34:38Z","title":"A Comprehensive Benchmarking Platform for Deep Generative Models in Molecular Design"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":50},"total_outbound_references":57},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2505.12848."}