{"as_of":"2026-08-10T19:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ad9cdc27d4a6c875394308a7eaa2f6bfeaac3a681f6dde95f1eacb32a2171f14","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:11:15.102648Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:11:28.623850Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":3,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.09023","snapshot_observed_at":"2026-08-06T16:11:28.623850Z","title":"Accelerating drug discovery through agentic ai: A multi-agent approach to laboratory automation in the dmta cycle","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17852","last_updated":"2025-07-18T17:57:40Z","snapshot_observed_at":"2026-08-10T11:04:53.623617Z","submitted_at":"2025-07-18T17:57:40Z","title":"Technical Implementation of Tippy: Multi-Agent Architecture and System Design for Drug Discovery Laboratory Automation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:11:28.623850Z"},"links":{"cited_paper":"/paper/2507.09023","citing_paper":"/paper/2507.17852"},"observation_digest":"sha256:f14b65e0ef21fa38a5efc76d989d0c5d82f925aed2bd61a5a9d18f904893fd78","observation_id":"94962245-e8cb-40ac-9c41-6016700041c9","resolution":{"observed_at":"2026-08-06T16:11:28.623850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"cited_work":{"arxiv_id":"2507.09023","doi":"10.48550/arxiv.2507.09023","metadata_source":"arxiv_reference","pith_arxiv_id":"2507.09023","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Accelerating drug discovery through agentic ai: A multi-agent approach to laboratory automation in the dmta cycle.arXiv preprint arXiv:2507.09023, 2025","venue":"arXiv (Cornell University)","work_id":"8be238aa-d388-486b-a94d-3c30ecda46d0","year":2025},"citing_paper":{"arxiv_id":"2604.05289","last_updated":"2026-04-07T00:47:37Z","snapshot_observed_at":"2026-08-01T18:59:29.157128Z","submitted_at":"2026-04-07T00:47:37Z","title":"FLARE: Agentic Coverage-Guided Fuzzing for LLM-Based Multi-Agent Systems","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T20:02:33.346701Z"},"links":{"cited_paper":"/paper/2507.09023","citing_paper":"/paper/2604.05289"},"observation_digest":"sha256:c705b5ce7da4175b60fdeb044b5821bbcea85e5033c01b4d6087814dc49679b1","observation_id":"d28a890e-ab4c-400c-98a3-d424601170f1","resolution":{"observed_at":"2026-05-10T20:05:45.690657Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"cited_work":{"arxiv_id":"2507.09023","doi":"10.48550/arxiv.2507.09023","metadata_source":"arxiv_reference","pith_arxiv_id":"2507.09023","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Accelerating drug discovery through agentic ai: A multi-agent approach to laboratory automation in the dmta cycle.arXiv preprint arXiv:2507.09023, 2025","venue":"arXiv (Cornell University)","work_id":"8be238aa-d388-486b-a94d-3c30ecda46d0","year":2025},"citing_paper":{"arxiv_id":"2605.27853","last_updated":"2026-05-27T02:11:23Z","snapshot_observed_at":"2026-07-06T23:37:31.844094Z","submitted_at":"2026-05-27T02:11:23Z","title":"MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T12:46:58.330103Z"},"links":{"cited_paper":"/paper/2507.09023","citing_paper":"/paper/2605.27853"},"observation_digest":"sha256:00b639015320e2f5d1f93c14241e108c99b40e63d392c8f3aaee2f8ffa1b8a44","observation_id":"3db628a7-eff4-49a5-9629-a50ed5f15773","resolution":{"observed_at":"2026-06-29T12:53:26.812959Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.09023/citation-record","integrity":"/paper/2507.09023/integrity","json":"/paper/2507.09023/citation-record.json","paper":"/paper/2507.09023"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:11:17.374097Z","title":"Artificial intelligence in drug development","venue":null,"work_id":"1b6a4059-247b-419a-accb-8512e97e4353","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:10:20.105674Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:e2be447f58368de8551f649bcf1b6326fee50512a36d4297fe2529b0fdf5627c","observation_id":"1918a0c4-0c09-42ca-b7d3-6649eac95aa4","resolution":{"observed_at":"2026-08-06T18:11:17.428196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:17.224415Z","title":"Academic drug discovery units in the uk: Progress and challenges","venue":null,"work_id":"27896f8f-a4ae-49c8-bb05-eac5e694b8f6","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.268463Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:b2848ea15c29d00f55d4a4575bb0c579f29a54d7cfe9646c7778bb79feb8f37b","observation_id":"c0f735aa-f5c6-41ee-8e3e-5f230c3195d3","resolution":{"observed_at":"2026-08-06T18:11:17.275380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:17.152480Z","title":"Harnessing network pharmacology in drug discovery: an integrated approach","venue":null,"work_id":"d76efdda-fe75-4ee2-a73e-36cf9017703c","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.343704Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:3bf13ee2c2dd46831cd1cf925043457115ed9f4c9695105ba8320882d650613d","observation_id":"58efb7b2-1494-47ec-b20c-3c56b1131db1","resolution":{"observed_at":"2026-08-06T18:11:17.163543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:17.061716Z","title":"The strategies and politics of successful design, make, test, and analyze (dmta) cycles in lead generation","venue":null,"work_id":"5b460655-36f7-4cd3-a652-b1391cb5036e","year":2016},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.420515Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:788b22da35e243b19c85f96af12c2e030ec908a574fefe719b9c15fe7bc32405","observation_id":"585b1751-a7d5-44a6-9abb-f177eefb8d40","resolution":{"observed_at":"2026-08-06T18:11:17.129897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.961439Z","title":"Overcoming dmta cycle challenges: A unified ai-driven system for efficient drug design","venue":null,"work_id":"5e3f330a-56d2-47fc-9660-aa605ec9c9b5","year":2024},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.459650Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:328828b666be0e311ddd1f35a81be77c2c05266b88b3eb2a8b3fd07b3dc512ed","observation_id":"bcef0d53-76d5-4800-a8f0-b74e4b0ad71b","resolution":{"observed_at":"2026-08-06T18:11:16.999847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.845866Z","title":"Aug- menting dmta using predictive ai modelling at astrazeneca","venue":null,"work_id":"d7fb5a3d-4ef7-4a71-a6cc-c9ec6fca162c","year":2024},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.519981Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:cb552fc1e6920faafd9f2174fdbd12b9016a1b84e75cff848edb50591b13d0f8","observation_id":"cf2dabc2-7763-4bdb-adc1-4e840d03acbf","resolution":{"observed_at":"2026-08-06T18:11:16.907187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.700253Z","title":"Computational chemistry in drug lead discovery and design","venue":null,"work_id":"406a6ab3-20f5-47e7-886b-aea2ee0b8fd5","year":2019},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.563821Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:f72a1d260b2a2f2bff71fe6e6b49fe69676e5dd6c0c76f17a118b760401f06da","observation_id":"3fcb6027-5857-4c06-90bb-f0bbc1a1aa78","resolution":{"observed_at":"2026-08-06T18:11:16.771457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.516921Z","title":"Deep learning methods for small molecule drug discovery: A survey","venue":null,"work_id":"4593b15e-e5a1-478d-9585-0c7d1fa41852","year":2023},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.612082Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:de40d83d3f3e74df4d0d3bdf15d45cc01364c2bd6f5534d445f8ce4025b3d4e0","observation_id":"b71e8442-d6a1-49fd-a535-b1bed65f1f2f","resolution":{"observed_at":"2026-08-06T18:11:16.619876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.396015Z","title":"Identifying rna-small molecule binding sites using geometric deep learning with language models","venue":null,"work_id":"506fa0fa-4a4d-4115-8314-7e0033e6aba4","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.691399Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:30a67a8f9e1dba911c567c5b3f8e63407d5e714d96355482f9d83ea08109bc37","observation_id":"17b82380-5bb6-4420-ab35-79b873a79c4e","resolution":{"observed_at":"2026-08-06T18:11:16.450208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.259962Z","title":"Computational drug design: a guide for computational and medicinal chemists","venue":null,"work_id":"176a49dc-dbc1-49b6-8588-e466888536ce","year":2009},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.756276Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:b152d8658b2935bd9d41053be5ead8582f11545a32702e12155c88f1c8168e57","observation_id":"88e0c54c-1510-47e4-90b2-a7d91712d775","resolution":{"observed_at":"2026-08-06T18:11:16.321930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:16.152146Z","title":"Current status of computational approaches for small molecule drug discovery, 2024","venue":null,"work_id":"9b8dc929-fd50-4dd1-b61c-f3792783aa26","year":2024},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.816055Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:54ecf3cd677ac90c9f2ad9825bcbd68d50f1b42e0642b84fbdad33bc49ab3c6a","observation_id":"57ef052e-1fd6-4f5e-bc24-af7e7a2a3959","resolution":{"observed_at":"2026-08-06T18:11:16.247281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.975192Z","title":"Computational methods in drug discovery.Beilstein journal of organic chemistry, 12(1):2694–2718, 2016","venue":null,"work_id":"75cf61d8-2019-4f42-9249-a749447ca7cf","year":2016},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.840136Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:5b6ff9c7ae204a9f1be2599a361cc7ed864c345b85d7ea093e6ffe4d937c6b94","observation_id":"1bb11e5c-2095-4801-870c-b9646006ff7f","resolution":{"observed_at":"2026-08-06T18:11:16.048660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.864572Z","title":"Uncovering bottlenecks and optimizing scientific lab workflows with cycle time reduction agents, 2025","venue":null,"work_id":"0f461a75-0c08-4542-b61b-3bf67d7aecd2","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.880977Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:0bab23bc52c236924b6a0811391a1aa83da2b045e046b2ca39cd45da215a234c","observation_id":"bd312066-5dd8-4cd9-8d18-d22d3ebd5bee","resolution":{"observed_at":"2026-08-06T18:11:15.906133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.763674Z","title":"The role of agentic ai in shaping a smart future: A systematic review","venue":null,"work_id":"3a4c09da-9bb9-4c57-8172-10d6a9e78624","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.904734Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:d82a1d39206afd977ad820d86d26ccf2c4f85574707640d96badee021ec598bb","observation_id":"ce514170-bbbe-40a3-8a9e-73d50bc67ca9","resolution":{"observed_at":"2026-08-06T18:11:15.829556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.626871Z","title":"Industrial agentic ai and generative modeling in complex systems","venue":null,"work_id":"208814f9-2736-4fb4-873f-508c462d8210","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.927938Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:2131eb41894a54f9b89467efc93113e9f3816ee82e481cc26b1cada462a0bb0d","observation_id":"d443a985-5833-4a26-aaf9-d05bd51feb4d","resolution":{"observed_at":"2026-08-06T18:11:15.696132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.549291Z","title":"From prompt to platform: an agentic ai workflow for healthcare simulation scenario design","venue":null,"work_id":"5c71ec58-1c55-4af8-8e3a-e3bf5c8dbf49","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:14.959014Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:ff516e21649e4dd85542cb78560b39954e7d4fff95a10625d0ad0ff586691a0b","observation_id":"b8bed849-92f8-481f-8c4e-1adf950bc648","resolution":{"observed_at":"2026-08-06T18:11:15.572022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.399842Z","title":"Comprehensive review of artificial general intelligence agi, agentic ai and genai: Current trends and future directions","venue":null,"work_id":"2843bbc0-8664-4618-bbd5-7748ebd47461","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:15.009990Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:9e07787e39658a7ef4c58bf3641bffeb564d947cc6b468c8656f67530800652f","observation_id":"662f03c2-f224-4009-9c0f-850be76dd2cc","resolution":{"observed_at":"2026-08-06T18:11:15.481752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.307942Z","title":"Accelerating drug discovery with artificial: a whole-lab orchestration and scheduling system for self-driving labs, 2025","venue":null,"work_id":"789b7b62-a68c-4a13-a7da-11447ba1c34f","year":2025},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:15.061921Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:569331e79b3d4cb6fad66c20473d00a4ee83680e5a54a5daf71630c213c91f09","observation_id":"cb373dfd-54e9-428f-abe1-35484cdfe6cc","resolution":{"observed_at":"2026-08-06T18:11:15.339083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:11:15.202823Z","title":"What would you like to do today?","venue":null,"work_id":"bdcd0b07-8238-42c3-a320-2809d8abd8d5","year":2023},"citing_paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:11:15.102648Z"},"links":{"citing_paper":"/paper/2507.09023"},"observation_digest":"sha256:ae04e6ac4473f110c0c6feb9d3e56ac7436abf1cb96fafd04a0ee209cd5eb9e4","observation_id":"32f035b3-b2e1-4142-8abb-3cf892612afc","resolution":{"observed_at":"2026-08-06T18:11:15.261277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.09023","last_updated":"2025-07-11T21:13:13Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-10T14:45:22.422394Z","submitted_at":"2025-07-11T21:13:13Z","title":"Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":19},"total_outbound_references":19},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 3 inbound Pith citation observations for arXiv:2507.09023."}