{"as_of":"2026-08-11T09:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:93d36bcc53629ae5763f18fae8859bc0977ce582efd3baa06a8c4da7538ef942","coverage":[{"denominator":99,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":99,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":99,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":99,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2606.16517/citation-record","integrity":"/paper/2606.16517/integrity","json":"/paper/2606.16517/citation-record.json","paper":"/paper/2606.16517"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.23579","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T22:17:26.256553Z","title":"Bioreason: Incentivizing multi- modal biological reasoning within a dna-llm model.arXiv preprint arXiv:2505.23579","venue":null,"work_id":"8861aafe-4d29-48a0-9583-61217d78044d","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:e84116a39e6f4fbf4ebd4dbbea1ce0560ce2ffc58fe0930e327fdb380bd1118f","observation_id":"a20c7d98-b4c3-4b32-ae5d-991e3b9dc530","resolution":{"observed_at":"2026-07-01T07:55:31.012328Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.723085Z","title":"rbio1-training scientific reasoning llms with biological world models as soft verifiers.bioRxiv, pages 2025–08","venue":null,"work_id":"a5b04687-ee6c-4411-9771-d89443d621a5","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:48e395108d114498d361b12bb6544f8e96a303fc59909b04827dc08ef860baae","observation_id":"8ee550f2-3500-41be-8ffe-6fa307534992","resolution":{"observed_at":"2026-07-06T14:32:35.724283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.826959Z","title":"Bioreason-pro: Advancing protein function prediction with multimodal biological reasoning.bioRxiv, pages 2026–03","venue":null,"work_id":"74233fc4-cf46-4fa5-9468-333770e4a101","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:d856140c47db66fd8abf66a376ab48a9466718a4dbc7217f64ae819485da82b1","observation_id":"b29dd336-f399-489e-aaa5-104c838e8949","resolution":{"observed_at":"2026-07-06T14:32:35.828151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.663752Z","title":"Evolm: In search of lost language model training dynamics","venue":null,"work_id":"6fa61183-2497-4944-a106-a34e4b542c23","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:56e95466f0d54c8087280f52f7f4cfbd5639d22084598c6742d06bd4d1dff02d","observation_id":"816c229b-c3c4-47dc-a2c3-46e266c7810f","resolution":{"observed_at":"2026-07-06T14:32:35.665407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-10T14:27:07.512699Z","title":"Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638","venue":null,"work_id":"f01253de-58e9-4b0f-a91e-4ef797517a24","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:80b34770ec8e5ff56a3869888cff51df99ab59e71fd0d51ffda25197e58f2ea7","observation_id":"499ecdb0-624d-4737-9ecb-075955457fbc","resolution":{"observed_at":"2026-07-06T14:32:35.758610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.20571","last_updated":"2025-10-24T10:02:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-29T09:24:30Z","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","version":3},"cited_work":{"arxiv_id":"2504.20571","doi":"10.18653/v1/2024.acl-long.643","metadata_source":"pith","pith_arxiv_id":"2504.20571","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","venue":"cs.LG","work_id":"75a5258b-4143-4f2f-99f3-6d950a496305","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2504.20571","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:111bd295600bcc4a1281fe6300726127d9609f21fdd0ffd108e7d00fb209352d","observation_id":"f1bbcac1-8a10-4861-89e9-2b8793c6b517","resolution":{"observed_at":"2026-07-01T07:55:31.008268Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.714991Z","title":"Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? NeurIPS, 2025","venue":null,"work_id":"93b51d96-2766-42cc-a1de-0c012e1a5c5e","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:2094b5f8fdf0e72958dc2efc8e075cdacda87ff8c1c27dd2b1153b13a7755ef1","observation_id":"01f37643-6cbc-4316-8061-43b2abeb325a","resolution":{"observed_at":"2026-07-06T14:32:35.716775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.16812","last_updated":"2025-08-27T03:10:49Z","snapshot_observed_at":"2026-08-06T14:58:46.433391Z","submitted_at":"2025-07-22T17:59:03Z","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","version":2},"cited_work":{"arxiv_id":"2507.16812","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.16812","snapshot_observed_at":"2026-07-05T15:11:10.807862Z","title":"Megascience: Pushing the frontiers of post-training datasetsforsciencereasoning.arXivpreprint","venue":"cs.CL","work_id":"d21e62b1-0689-4840-b3b4-eea8eb829a15","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2507.16812","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:ed9a3298c9eb88d0b334561cfb31f01df234090b45b6c3dd11c6a0eb95858641","observation_id":"c207318a-eee8-496e-8268-a0f6e2abae2c","resolution":{"observed_at":"2026-07-01T07:55:31.053037Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.805226Z","title":"OpenThoughts: data recipes for reasoning models.ICLR, 2026","venue":null,"work_id":"2a3b33c3-d84d-4b3f-8b4a-21947221d93f","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:eb76a4ec1fafd198804a0e8ac84d01e47922b764bb1976591a31f6ef6cacdf79","observation_id":"5c6daebd-6c49-45fc-a62f-820dd64a65fb","resolution":{"observed_at":"2026-07-06T14:32:35.806378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.749646Z","title":"Scaling large language models for next-generation single-cell analysis.BioRxiv, pages 2025–04, 2026","venue":null,"work_id":"d68eb821-d3e7-437c-8d68-bfab24a7cbf1","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:d8b30624c88f4f791a9bc98609f618e635df1beb3e38739a84242aefd8d7e92e","observation_id":"c9507af8-2762-4e0e-bfb0-40d57a35795e","resolution":{"observed_at":"2026-07-06T14:32:35.750766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.761877Z","title":null,"venue":null,"work_id":"8312e62e-e6d2-4f1a-88c9-e97d98ea900f","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:699200dd18174c4a9c49c402f74bba5b649addd966c35ab96e34250b70498b7c","observation_id":"257b801a-42a2-4ede-96e9-14f9eb5e0e7d","resolution":{"observed_at":"2026-07-06T14:32:35.763077Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.743563Z","title":"Unleashing scientific reasoning for bio-experimental protocol generation via structured component-based reward mechanism.ICLR, 2026","venue":null,"work_id":"f1ad6437-463e-4c6a-a6d8-d78f36beedc2","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:f88825446ff38a3ff4b771aa3ca375ae04d740aef0854fd2b68a7e87e46191a8","observation_id":"c6dbf461-4e3b-4668-8bf3-f00b16fc8ff6","resolution":{"observed_at":"2026-07-06T14:32:35.744790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.810730Z","title":"Sci-verifier: Scientific verifier with thinking.ICLR, 2026","venue":null,"work_id":"1c52df7b-bea6-46a1-82b0-91bf8c3f04a4","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:7cb8bfae800c08852bbd1fb335bdf22975613a67dc21a3e26d77bf1a33330530","observation_id":"85be97a7-5171-49e1-90d4-78255164f763","resolution":{"observed_at":"2026-07-06T14:32:35.811973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.724985Z","title":"Cellduality: Un- locking biological reasoning in LLMs with self-supervised RLVR","venue":null,"work_id":"81d8078d-1697-4001-a46b-cb51c3e41592","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:d38544d1e0f1547373e299947c0055c57f19b4a19e173b5c42e088f7fca02df5","observation_id":"b42d105a-06c1-46e3-96ca-a5e50693e051","resolution":{"observed_at":"2026-07-06T14:32:35.726468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.821264Z","title":"VCWorld: a biological world model for virtual cell simulation.ICLR, 2026","venue":null,"work_id":"b8694cac-47ba-46c6-9d64-f3cda193ab14","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:ff7b4c74083ced6815e9ae851c261e7b8ca540357f84639edab9ecc4a8948eda","observation_id":"1b9f73cb-422a-4c9c-9a95-512ce6215d42","resolution":{"observed_at":"2026-07-06T14:32:35.822513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.814302Z","title":"Helix: Evolutionary reinforcement learning for open-ended scientific problem solving.ICLR, 2026","venue":null,"work_id":"847b3fff-190d-4715-9afe-b35e0cc50acc","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:dbddb13580b3cc9d3ca916aa4338511530952946e3981898dac7eb9a9e7968fb","observation_id":"511a44f2-54ac-4500-8c99-60c3aebe3af2","resolution":{"observed_at":"2026-07-06T14:32:35.815413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.745576Z","title":"Reshaping reasoning in llms: A theoretical analysis of rl training dynamics through pattern selection.ICLR, 2026","venue":null,"work_id":"1e6e2d1e-c661-4e5f-bb9e-27da54bb4ecb","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:a120ffc3a9f2217f7abd434e3a3a75d1bcc7395c0c9c66654bdc2f22016fb04d","observation_id":"a159b424-6f9a-4f14-b82e-8140af61d780","resolution":{"observed_at":"2026-07-06T14:32:35.746786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.702394Z","title":"Training dynamics impact post- training quantization robustness.ICLR, 2026","venue":null,"work_id":"f3ba36da-7db3-46b1-ac2f-9c512f279c12","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:15a94b6a46c229d56e7a795157e240eaf15605d06e5ddf0aa2f0546c938be10a","observation_id":"13c30a8b-7aeb-4536-91f1-b8e5e5526430","resolution":{"observed_at":"2026-07-06T14:32:35.705513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.717410Z","title":"The coverage principle: How pre-training enables post-training.ICLR, 2026","venue":null,"work_id":"2ffc9dd4-4fdf-4411-b1d3-9d17ca629d7d","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:cfa591d9c5caa9271303931150d01aaf05f3f7201928d4fd254f4241ee6ffb0e","observation_id":"575be23d-0c70-4665-99c8-ebe38865670a","resolution":{"observed_at":"2026-07-06T14:32:35.718551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.819591Z","title":"Benchmarking algorithms for generalizable single-cell perturbation response prediction.Nature Methods, 23(2):451–464","venue":null,"work_id":"a932c64d-9c46-44ec-b57d-868820aa151c","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:bf2f58a738faad40407da571b35628d636ad4bf82486e8638617253922476a3d","observation_id":"e7c480c4-c8c9-4abb-961b-dcdf2f10a011","resolution":{"observed_at":"2026-07-06T14:32:35.820779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.751623Z","title":"A fully automated benchmarking suite to compare macromolecular complexes.Nature Methods, 23(2):387–394, 2026","venue":null,"work_id":"64c005df-5d01-4ea6-9139-71d07c0dc79b","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:39426b93e6542a264cec34ffd28abaa767c324e2d9ce090ae4de10555407d597","observation_id":"a01c3af3-411e-4356-96e6-f3aaf6f4e2c0","resolution":{"observed_at":"2026-07-06T14:32:35.752761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.759658Z","title":"PLINDER: the protein-ligand interactions dataset and evaluation resource.BioRxiv, pages 2024–07, 2024","venue":null,"work_id":"8a44f625-2e15-4e02-ac0d-ff83dabb37bb","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:95af4cbdaac3628c1a06ae97111eec9642c65fbb5f5c9a0d229dc867fabc20de","observation_id":"08b8a02b-a6e4-496f-8e0e-04274492f39e","resolution":{"observed_at":"2026-07-06T14:32:35.761050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.781980Z","title":"ProCyon: a multimodal foundation model for protein phenotypes.BioRxiv, pages 2024–12, 2025","venue":null,"work_id":"1f7da7a7-e712-437c-9661-3670b4e39194","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:1771ffbe26b75657df45018f3d77d8329077e1d184dbba1eeee08fa5156577dc","observation_id":"f0b8d022-7eb5-40b7-81b3-c2dac3b9463f","resolution":{"observed_at":"2026-07-06T14:32:35.783200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.799838Z","title":"Evaluating generalizability of artificial intelligence models for molecular datasets","venue":null,"work_id":"2ba96e4c-aa1a-4761-a176-613adfd41796","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:8becaf806716947a8e8c95752e7f73316666c0b03966882b650860711ace8e9f","observation_id":"ce89901b-490e-491e-b055-8a9657b7d5cb","resolution":{"observed_at":"2026-07-06T14:32:35.800994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.783973Z","title":"Zero-shot evaluation reveals limitations of single-cell foundation models.Genome Biology, 26(1):101, 2025","venue":null,"work_id":"532e7b1f-a1c1-41e7-bb44-c6a25c2585e0","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c4992889caae4184c8628337ffe7c0924dd6a87dcd918b10d8d08e7568b013ad","observation_id":"848fbc79-e7eb-4adc-96ea-a5456fefaa0e","resolution":{"observed_at":"2026-07-06T14:32:35.785271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.797909Z","title":"Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines.Nature Methods, 22(8):1657–1661","venue":null,"work_id":"8fb3a187-dbfd-478b-a071-99727993fd58","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:3d27b98361cf75e7aa23d731dffb29431585bdb0c9d224852bbbfed30b772a76","observation_id":"a867ed26-1b31-4416-9e05-1c92b4df6512","resolution":{"observed_at":"2026-07-06T14:32:35.799179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.763771Z","title":"LoongRL: reinforcement learning for advanced reasoning over long contexts.ICLR, 2026","venue":null,"work_id":"dbf1601a-4779-4b67-a713-4203223aa355","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:5c0614785061a577c1b30207f81b07bbdfc29172d8f8463b51260a184e32d065","observation_id":"896eb9a7-0c99-4a86-85ee-8191caf68737","resolution":{"observed_at":"2026-07-06T14:32:35.764879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.790453Z","title":"The art of scaling reinforcement learning compute for llms.ICLR, 2026","venue":null,"work_id":"6dca00b7-a0d4-4d15-8924-3911585dcf37","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c51b743986123737fef549acdad2f50c523050a79f7304172635e5619170b67f","observation_id":"b73ba19c-281b-40fb-9d52-4efc77c1b216","resolution":{"observed_at":"2026-07-06T14:32:35.792045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.796008Z","title":"Rethinking LLM reasoning: From explicit trajectories to latent representations","venue":null,"work_id":"e5a4fa32-d3a7-4df5-aa5b-1b18d706e6fe","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:81f5d5a6eee6bedec6852dbfe9c1e927e9529eafc8a396d537d5130ce139906f","observation_id":"755c69e7-dfac-4b11-aff4-6cce47a5afb2","resolution":{"observed_at":"2026-07-06T14:32:35.797233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.817836Z","title":"CoT-Evo: evolutionary distillation of chain-of-thought for scientific reasoning.ICLR, 2026","venue":null,"work_id":"916c6b93-3e36-48a9-b496-b5ea51524e8c","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:eae3fd1ebb658bd9ef05f6362b45bc33d7b2840846dcc25c9648e8afd51b913e","observation_id":"032e4c82-084c-4ab7-bf53-53aaee1aefea","resolution":{"observed_at":"2026-07-06T14:32:35.819079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.650686Z","title":"scPilot: Large language model reasoning toward automated single-cell analysis and discovery.NeurIPS, 2025","venue":null,"work_id":"77646d2f-2dd9-44e3-82cb-f265d3a23906","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:783a0a7e599da1c7183376aa5990825a61af425070a84208905c230e16955173","observation_id":"b416dea7-b882-4a1d-ac06-b6ea7a33cf7b","resolution":{"observed_at":"2026-07-06T14:32:35.652371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.661449Z","title":"AI-researcher: autonomous scientific innovation.NeurIPS, 2025","venue":null,"work_id":"7997d116-677e-48d2-b82f-23f8f807bcfc","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:dbfe485de7fffbecac8217858e553053d260d7528b6116003dcae2f710bb5427","observation_id":"bd4168e3-c90f-4ff7-b800-e511d532242e","resolution":{"observed_at":"2026-07-06T14:32:35.663167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.768750Z","title":"Training a scientific reasoning model for chemistry.NeurIPS, 2025","venue":null,"work_id":"7bee1333-e9ce-4a8c-bf38-88704768d186","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:32082f5636f833db90b8f53929ffd39e64a8e43c89d701790d5cf95a4051deef","observation_id":"fad6bc51-644e-40b9-ad54-89fdaebf3bdc","resolution":{"observed_at":"2026-07-06T14:32:35.770421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.775604Z","title":"Language models for biological research: a primer.Nature Methods, 21(8):1422–1429","venue":null,"work_id":"3cbecd4f-89f0-4add-ae0f-79cda18f2347","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:9e421cfff162c4177840a9b16544037057c15e6e4bd992b2404c9c566e6a0f85","observation_id":"a8d2161a-d832-4c5d-ac22-6e8621d226fc","resolution":{"observed_at":"2026-07-06T14:32:35.777113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.771340Z","title":"Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome.Bioinformatics, 37(15):2112–2120","venue":null,"work_id":"3a0bf94c-9ef1-47fd-a115-2a109ba038dd","year":2021},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:35defc9a6733c7bdf35b52d95fd9e1e74f0901f957cca9a7217e6613aaf4796a","observation_id":"6baa52b6-fdba-4d49-a65e-3a400d7c4ad0","resolution":{"observed_at":"2026-07-06T14:32:35.773048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15006","last_updated":"2024-03-18T23:59:29Z","snapshot_observed_at":"2026-08-10T14:19:30.832416Z","submitted_at":"2023-06-26T18:43:46Z","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","version":2},"cited_work":{"arxiv_id":"2306.15006","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.15006","snapshot_observed_at":"2026-07-03T03:57:38.576237Z","title":"Dnabert- 2: Efficient foundation model and benchmark for multi-species genome","venue":null,"work_id":"e76887ae-a155-45c6-a434-54de363e9e3c","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2306.15006","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:4cdeddef40bcd13f53b3735e44ec83f5c5275a8f6a1b8c9b43844ed734cd5280","observation_id":"2eeb9d5a-7574-4dad-b1c5-9b1cef876972","resolution":{"observed_at":"2026-07-01T07:55:31.056974Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.778036Z","title":"Sequence modeling and design from molecular to genome scale with evo.Science, 386(6723):eado9336","venue":null,"work_id":"fa2cbd38-b9d7-46af-9c1d-f22c59a1c480","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:e7ef4970e475d0921aacd2b8fe260d9efd4a58aa6b865de2c1fe0eeba678dd46","observation_id":"071b65ba-0a11-45a8-ba57-1b270c13a889","resolution":{"observed_at":"2026-07-06T14:32:35.779263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.803300Z","title":"Genome modelling and design across all domains of life with evo 2.Nature, pages 1–13","venue":null,"work_id":"74d004bd-4a0d-4e10-9f85-4892cd7b1da9","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c2be520788733ba17e12136522bc3136a508796cda307b5c76bd5ae85268a12c","observation_id":"cc7196dc-d36d-4efb-a395-c897fad90770","resolution":{"observed_at":"2026-07-06T14:32:35.804438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.816007Z","title":"Nucleotide transformer: building and evaluating robust foundation models for human genomics.Nature Methods, 22(2):287–297","venue":null,"work_id":"c58b3e10-d216-4a2a-9f7f-3656004e428a","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:e62391a8c4338891d0b634f707bad752754ddff5c3b8147b979f767c35d43194","observation_id":"5e5066e0-af51-4f73-94db-ce8e00b3b2d2","resolution":{"observed_at":"2026-07-06T14:32:35.817254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.824957Z","title":"Alphagenome: advancing regulatory variant effect prediction with a unified dna sequence model.BioRxiv, pages 2025–06, 2025","venue":null,"work_id":"b376a4d9-7239-4090-bd37-6dcd6962023f","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:90ce42b3cbbe029601c72bf5d2f62c972ddae914edd82ed27cbe72a8f885f653","observation_id":"06e0b40c-1c35-4e32-99aa-ec2e705723ef","resolution":{"observed_at":"2026-07-06T14:32:35.826186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.711180Z","title":"The omg dataset: An open metagenomic corpus for mixed-modality genomic language modeling.bioRxiv, pages 2024–08, 2024","venue":null,"work_id":"493e6d46-084c-47b2-9338-47e810a3e4bd","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:1e2a2ac923386297eb102e516f27bb8f011fa76ab2b00253af7ca34440fad8ec","observation_id":"ddc087a6-56aa-42b8-b8be-3db7a9bddf7c","resolution":{"observed_at":"2026-07-06T14:32:35.712431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.05775","last_updated":"2026-04-07T12:14:23Z","snapshot_observed_at":"2026-07-06T22:54:26.231593Z","submitted_at":"2026-04-07T12:14:23Z","title":"PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?","version":1},"cited_work":{"arxiv_id":"2604.05775","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.05775","snapshot_observed_at":"2026-07-01T07:55:31.058533Z","title":"PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?","venue":"cs.CL","work_id":"6a6107a1-b736-401b-8df7-82f82ae81f59","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2604.05775","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:cb63bab047b77ed854b7c376fae86dcd7c3c1162e1502a8163558afef8777b88","observation_id":"8b5d8dcd-840e-4ffa-80ca-4d551619f7fd","resolution":{"observed_at":"2026-07-01T07:55:31.060469Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.653152Z","title":"Orthrus: toward evolutionary and functional rna foundation models.Nature Methods, pages 1–11, 2026","venue":null,"work_id":"5dd424a8-f650-4209-aa80-d71216b3c01f","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:728dd86d16f3a6a4dd76a5b3d96a51b0b60b4c5ac6b152a473825243f5895057","observation_id":"f8295647-a75c-4943-bcd5-8bb9ba879c3e","resolution":{"observed_at":"2026-07-06T14:32:35.654855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.00300","last_updated":"2022-08-08T00:49:01Z","snapshot_observed_at":"2026-07-06T12:55:38.555576Z","submitted_at":"2022-04-01T09:10:31Z","title":"Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions","version":5},"cited_work":{"arxiv_id":"2204.00300","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.00300","snapshot_observed_at":"2026-07-03T23:49:02.995310Z","title":"Interpretable","venue":null,"work_id":"7e036598-5dc7-43fb-88d5-e1f23ab893a5","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2204.00300","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:435891049182aa2bc29995e25d148b9a30d448c81418d5c143942b601fa99df2","observation_id":"2c78f641-bbaa-4ece-bbb3-7b7bcd1b7c51","resolution":{"observed_at":"2026-07-01T07:55:31.052546Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.706728Z","title":"A cross-species generative cell atlas across 1.5 billion years of evolution: The transcriptformer single-cell model.bioRxiv, pages 2025–04, 2025","venue":null,"work_id":"a2abce1f-6395-44b3-9205-2db0871b4d05","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c64fb1eae9f523bc6c292621d41b28e85fc478d1941e35dfcd062df5eeee7037","observation_id":"a7e05066-7bb3-4291-9d24-5eab03f1024d","resolution":{"observed_at":"2026-07-06T14:32:35.708126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.747590Z","title":"scgpt: toward building a foundation model for single-cell multi-omics using generative ai","venue":null,"work_id":"4973ae22-ca23-4b1e-8c22-8dda822edaa6","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:b5d64b917a339a3857c21f067b0e43b1512de387393d7b149336965dc5030032","observation_id":"4c0de922-8f47-4581-96b9-8310ef5d9f1e","resolution":{"observed_at":"2026-07-06T14:32:35.748740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.808973Z","title":"Transfer learning enables predictions in network biology.Nature, 618(7965):616–624","venue":null,"work_id":"d9350371-8037-4b52-bfb3-fd672eba7c11","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:6d61ca2177770a164e83f46c1fe5cbc26fb9b96ec41804e850e92c433ec8ed2e","observation_id":"b1cda3db-3dba-4869-aa03-bfabd5156de8","resolution":{"observed_at":"2026-07-06T14:32:35.810228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.709015Z","title":"Predicting cellular responses to perturbation across diverse contexts with state.BioRxiv, pages 2025–06, 2025","venue":null,"work_id":"8aeb18f2-98bd-47cb-bb92-6483e09b753d","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:3e7b3a8dba7d7009f8d334fdc8e6ec782ffdf3bced7e8dfa6e883701d403cafe","observation_id":"ed4a13bd-39dc-46ee-8f6e-a82e6b13d112","resolution":{"observed_at":"2026-07-06T14:32:35.710502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.755378Z","title":"Large-scale foundation model on single-cell transcriptomics.Nature methods, 21(8):1481–1491, 2024","venue":null,"work_id":"7e623721-f52f-4380-9b23-3549136a6411","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:9c3ca93dcd00c826e711c1c1eaba2d296f3b3a318acf5e712eafeb3ac70cf287","observation_id":"551887b9-4070-4c7f-b6a4-9492b365dfcb","resolution":{"observed_at":"2026-07-06T14:32:35.756603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.785943Z","title":"scgenept: Is language all you need for modeling single-cell perturbations?bioRxiv, pages 2024–10, 2024","venue":null,"work_id":"da37cc89-8de9-4fb5-9377-19b7a44b19e4","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:b17184be9cd10de465ce02115bb96832080dc85791ebe48786d904a7f7a58324","observation_id":"d9eceec1-310f-4ba8-9dbc-eafd572fe9fc","resolution":{"observed_at":"2026-07-06T14:32:35.787214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-08T00:24:23.153874Z","title":"Evolutionary-scale prediction of atomic-level protein structure with a language model.Science, 379(6637):1123–1130","venue":null,"work_id":"38aa064a-23d4-47be-bf50-efe3e175717b","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:3f0edb6e43b5859d69691fe9580360e198d98b0aad04b70fafa30669db1f0b93","observation_id":"19e5960b-4067-4e18-896a-9f261b3045b2","resolution":{"observed_at":"2026-07-06T14:32:35.808395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-08T12:44:54.321505Z","title":"Simulating 500 million years of evolution with a language model.Science, 387(6736):850–858","venue":null,"work_id":"30050362-f781-47b2-a9aa-88655da87165","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:aaf3fc2f8afaacd04662aff5ed0a2aa3a958170385ef5397d24706a0d2e85a00","observation_id":"dccdf8fe-4535-4ab0-bcc7-4bbebdb27c4c","resolution":{"observed_at":"2026-07-06T14:32:35.824434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.669223Z","title":"Progen2: exploring the boundaries of protein language models.Cell systems, 14(11):968–978","venue":null,"work_id":"3e4f96b5-cf4c-44eb-b9c6-a9687d70f1f8","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:0073323e316eb1a68557a943d23300856e628cf0e7a3a728fb4afce0b9d2b1a4","observation_id":"3b2f2671-9088-408d-ae26-d2e0736f6242","resolution":{"observed_at":"2026-07-06T14:32:35.701409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.765642Z","title":"Unified rational protein engineering with sequence-based deep representation learning","venue":null,"work_id":"c9893997-ecd9-407d-96cd-7da562139894","year":2019},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:a68bb68ac3e070cd3141ef4aa25b47a4b6200dccf2e169b9cdad3afa4824730c","observation_id":"b6d63400-b20d-4151-8746-e38f823624ae","resolution":{"observed_at":"2026-07-06T14:32:35.767928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.658711Z","title":"Multimodal learning enables chat-based exploration of single-cell data.Nature Biotechnology, pages 1–11","venue":null,"work_id":"b09d0085-7893-4de1-a454-dbb23a72e027","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:cdd112edcdd0cefa5106d97fbf08e87de03becdf85ceaf88aa740468c71727f6","observation_id":"5d45e374-085d-4059-9001-c2f43a8fb6e0","resolution":{"observed_at":"2026-07-06T14:32:35.660354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-09T18:16:26.555721Z","title":"Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744","venue":null,"work_id":"aa3e2ba7-4265-495b-8612-615b2ddc9991","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:a99cf1d880d2b199e03afd2ccea6e0b1ae80adcb803c96f7cf589620dbb44d55","observation_id":"b0033596-67b7-40e5-9396-11162249271c","resolution":{"observed_at":"2026-07-06T14:32:35.738517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.812496Z","title":"D-cpt law: Domain-specific continual pre-training scaling law for large language models.Advances in Neural Information Processing Systems, 37:90318–90354, 2024","venue":null,"work_id":"8b4f1603-d498-4866-99bf-be84fdff7a72","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:d2405b2cf0d167d59d4eb228fc391a0277fd5a95613932bb66128da9c233996a","observation_id":"2b5eb6f2-2725-4b83-8286-9a22ed96748e","resolution":{"observed_at":"2026-07-06T14:32:35.813782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.727252Z","title":"Understanding the effects of RLHF on LLM generalisation and diversity","venue":null,"work_id":"64ce7de9-250c-4421-8fd3-564e2dc92084","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:56dcdd1f9e27d05ce84ec110b280db7a8ff3259542847ef4b206241e9360a030","observation_id":"72363057-8c18-4cc9-9655-7f1b18f974c4","resolution":{"observed_at":"2026-07-06T14:32:35.728496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.647290Z","title":"Don’t stop pretraining: Adapt language models to domains and tasks","venue":null,"work_id":"5e410ed4-8767-48e5-b492-277342145950","year":2020},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:255e44b46876308d4fcc3ec48a1f71c51467d5edfc70bc62eba7028e78eb13a0","observation_id":"7ecf1744-098d-48de-ba3d-415a441462f9","resolution":{"observed_at":"2026-07-06T14:32:35.649349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":"2001.08361","doi":"10.1145/3616855.3635845","metadata_source":"pith","pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Laws for Neural Language Models","venue":"cs.LG","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","year":2020},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:61e2d69c0ec7e18caac75afcf75ff216a01158feccf4d776df563b0b8425b59a","observation_id":"ab08da76-09d0-4933-ada7-d1ed2e027c0e","resolution":{"observed_at":"2026-07-01T07:55:31.024748Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.731034Z","title":"Training compute-optimal large language models","venue":null,"work_id":"cf2adcee-e5c1-4364-8f3a-049ec0f21273","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:0ec3cebec839f0ce6cd909b91a0907ce538e7176601c22421ef8f4e986591c57","observation_id":"5f10e1e4-de71-4874-b727-e30b5e443897","resolution":{"observed_at":"2026-07-06T14:32:35.732234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.779850Z","title":"Pythia: A suite for analyzing large language models across training and scaling","venue":null,"work_id":"1e6c838f-b659-4bad-a3a5-73406eb5d1dd","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:6b4db563f784b1866f374b7e3de630b4a93b26970ed128efc57fea444b6548bc","observation_id":"fdce36f1-ba12-4b03-943d-6b308e16b38d","resolution":{"observed_at":"2026-07-06T14:32:35.781141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.741456Z","title":"When scaling meets LLM finetuning: The effect of data, model and finetuning method","venue":null,"work_id":"6d217fcc-aa96-4878-8bd2-80ae620bc716","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:7fa496d5b13818230f77d70ab2430b9de7876ee4935704c7e2c2a5d314077b18","observation_id":"fea5dd5f-9af4-4673-af6b-0a8c9d4ab3a7","resolution":{"observed_at":"2026-07-06T14:32:35.742642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.04014","last_updated":"2023-09-06T23:13:07Z","snapshot_observed_at":"2026-07-06T16:03:42.855570Z","submitted_at":"2023-08-08T03:18:18Z","title":"Continual Pre-Training of Large Language Models: How to (re)warm your model?","version":2},"cited_work":{"arxiv_id":"2308.04014","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.04014","snapshot_observed_at":"2026-07-04T18:40:03.356996Z","title":"Continual pre-training of large language models: How to (re) warm your model?","venue":null,"work_id":"881d21e0-b9b0-4031-a085-cf950213fe5e","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2308.04014","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:7098fedd4b1031a54ab4ed46aa7ab2291138fc0eb251aeac3ab9c77ee51c542b","observation_id":"f108a764-8d7c-4684-bfc9-62af0f54910c","resolution":{"observed_at":"2026-07-01T07:55:31.039643Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08763","last_updated":"2024-09-04T16:13:18Z","snapshot_observed_at":"2026-07-06T17:44:09.081164Z","submitted_at":"2024-03-13T17:58:57Z","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","version":4},"cited_work":{"arxiv_id":"2403.08763","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08763","snapshot_observed_at":"2026-07-04T18:40:03.364876Z","title":"Ibrahim, B","venue":null,"work_id":"74c611cb-0d0e-46d7-8fa5-ad6a5196fa2c","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2403.08763","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:9da4ec2e1084f94e1274f0a924f12849e3f863e5dc7aa5e0f172d6f516495626","observation_id":"0e975219-56d7-4054-bb91-6b67d87a5fb2","resolution":{"observed_at":"2026-07-01T07:55:31.044759Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07263","last_updated":"2024-07-09T22:37:59Z","snapshot_observed_at":"2026-08-07T09:28:48.845112Z","submitted_at":"2024-07-09T22:37:59Z","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models","version":1},"cited_work":{"arxiv_id":"2407.07263","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.07263","snapshot_observed_at":"2026-07-03T16:38:40.742383Z","title":"Reuse, don't retrain: A recipe for continued pretraining of language models","venue":null,"work_id":"61784e94-998c-450a-93a4-550901ac1844","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2407.07263","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:f0af4df61f7378aac8a516670829589c51000fd18ee4f2bba559012e415a378d","observation_id":"18fcd226-fa99-4f15-8010-3f13a9de0adf","resolution":{"observed_at":"2026-07-01T07:55:31.048963Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.739522Z","title":"Continual pre-training of language models","venue":null,"work_id":"c044726a-ab97-45cc-b470-f0a32889b948","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:b68b982a1b5950a59d72b111204a00fc73d52c6344ea77ce23184eccb9f43a59","observation_id":"6984a660-002e-4fb4-b5e5-71f4bfe32bb6","resolution":{"observed_at":"2026-07-06T14:32:35.740716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.09530","last_updated":"2024-07-25T03:08:18Z","snapshot_observed_at":"2026-08-04T15:46:28.843449Z","submitted_at":"2023-09-18T07:17:52Z","title":"Adapting Large Language Models to Domains via Reading Comprehension","version":4},"cited_work":{"arxiv_id":"2309.09530","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.09530","snapshot_observed_at":"2026-07-01T07:55:31.038358Z","title":"Jeffrey Cheng, Marc Marone, Orion Weller, Dawn Lawrie, Daniel Khashabi, and Benjamin Van Durme","venue":null,"work_id":"6b5be8c8-fbb2-433d-859d-0d45909f890b","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2309.09530","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:2a9172de7312165cc7619c394c8873363f2ea0d0f7c73d73e26bdbb9ea552017","observation_id":"c7117178-3b1a-4c95-b591-54621d51d14f","resolution":{"observed_at":"2026-07-01T07:55:31.040486Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.729122Z","title":"Composer 2 technical report, 2026","venue":null,"work_id":"f2147ab8-8f92-40b0-b552-ef81c3f3d18a","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:195d3b67012e3039780b3281caa37eb18848d0af9367d7444acb5b0cb8be10cd","observation_id":"308dd23d-ddd4-4092-a582-633c43cd30d2","resolution":{"observed_at":"2026-07-06T14:32:35.730144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.721106Z","title":"Sft memorizes, rl generalizes: A comparative study of foundation model post-training","venue":null,"work_id":"9e8a0d35-4199-40c2-8aad-4d3df8568a67","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:7fd80f0a19ae78de41c536fba7f74446f2fe91dfd0851f3dc296bd198bf03948","observation_id":"12a49980-a0ab-400a-a6ba-96471262abcc","resolution":{"observed_at":"2026-07-06T14:32:35.722288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.655746Z","title":"Gene-r1: Reasoning with data- augmented lightweight llms for gene set analysis","venue":null,"work_id":"fbad1595-8afb-40b9-8db3-1f545309c4ea","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:47ea43383f0be77f818d675807183b187c5f31c38e49a78ae6c44975ced959be","observation_id":"d362e53c-7dd7-4d5f-8c51-88397c8c4b75","resolution":{"observed_at":"2026-07-06T14:32:35.657209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19501","last_updated":"2025-06-02T21:31:08Z","snapshot_observed_at":"2026-08-11T00:30:55.892570Z","submitted_at":"2025-05-26T04:28:46Z","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.19501","doi":"10.48550/arxiv.2505.19501","metadata_source":"arxiv_reference","pith_arxiv_id":"2505.19501","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Genome-bench: A scientific reasoning benchmark from real-world expert discussions.CoRR, abs/2505.19501","venue":"ArXiv.org","work_id":"86f127ee-78d9-4c85-a383-2dcf2f767b39","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2505.19501","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:e14b681572171be05dee5d5c1aa22b38341886c4105f0e43e29cf7603716ed20","observation_id":"ca5363fa-0429-4cc9-82e4-98d5859b14cb","resolution":{"observed_at":"2026-07-01T07:55:31.065267Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.793695Z","title":"Medea: An omics ai agent for therapeutic discovery.bioRxiv, pages 2026–01, 2026","venue":null,"work_id":"6ea14560-81ac-4fa9-a8cf-a6de3d099d78","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:aff14680ca42c6dfa183a8f0cb142147a550dad607497cd15d60e169d7ff6b61","observation_id":"27a3d72a-1056-459c-bf2c-a4096d5a5c20","resolution":{"observed_at":"2026-07-06T14:32:35.795469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.828846Z","title":"Interpro in 2022.Nucleic acids research, 51(D1):D418–D427, 2023","venue":null,"work_id":"d01df3c6-0507-4012-b391-f653c85f3f55","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:bc638df67c62612c87147b0329c63b1630bc843e8c4d2e587989c176f617e935","observation_id":"4889816c-966e-4027-bf87-512056324207","resolution":{"observed_at":"2026-07-06T14:32:35.829995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:e1664a78562fff1ec019cc990cffa1eaf5eca9289a0d217a9f1596ce7f1e003f","observation_id":"115bece9-112f-4e64-875e-965b38192a47","resolution":{"observed_at":"2026-07-01T07:55:31.034809Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.801570Z","title":null,"venue":null,"work_id":"e7419715-b86f-41f0-af12-b1ed4a81fc39","year":2026},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:4f0886c8f872a54f2510a63d3bedae83ed808dab216fa504af399ba589c822a8","observation_id":"f64de101-63c8-4b4b-bfc9-25925a4b8f4d","resolution":{"observed_at":"2026-07-06T14:32:35.802667Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.713104Z","title":"FineFineWeb: A comprehensive study on fine- grained domain web corpus","venue":null,"work_id":"cae5507f-ae2b-42ce-895a-6192aaf24247","year":null},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:7e8d18cca69ac57f06670675c822a25eab9fe0ec084ae33627affdb70498c04f","observation_id":"b9679af1-fdbf-4e86-bb53-5b93f05a84f9","resolution":{"observed_at":"2026-07-06T14:32:35.714422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.719115Z","title":null,"venue":null,"work_id":"0143f156-e1ec-4b63-b499-0b7f6298eded","year":null},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:a0457a960406acc6f3b8112ee64618988da932b5f8df49f71e891c09c9c129f2","observation_id":"f2b2cadd-15cc-43e8-bdff-913b75f58cbb","resolution":{"observed_at":"2026-07-06T14:32:35.720343Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/28.1.27","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"KEGG: Kyoto Encyclopedia of Genes and Genomes","venue":"Nucleic Acids Research","work_id":"7e9f7570-8661-49f8-bc58-f15bff20d76f","year":2000},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:317d3ba4f95343660f08c9b1c32e39f181da6e2139d00d0d44515a77db55c99a","observation_id":"3eb1caf4-1266-4ae5-8bd1-752a63fbec1e","resolution":{"observed_at":"2026-07-01T07:55:30.320351Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-11T01:19:58.849806+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T01:19:58.849806+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gky962","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"New approach for understanding genome variations in KEGG.Nucleic Acids Research, 47(D1): D590–D595, 2019","venue":"Nucleic Acids Research","work_id":"0f0d14d0-0f6b-4baa-94fc-dcc00654c849","year":2019},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:4de667bda4c4b13fc26436339776a0dc0833e9d583ba1dcf193a3161340d56a5","observation_id":"963eead3-b552-4e9d-b70d-607d94754268","resolution":{"observed_at":"2026-07-01T07:55:30.300204Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gkz972","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ClinVar: improvements to accessing data.Nucleic Acids Research, 48(D1):D835–D844, 2020","venue":"Nucleic Acids Research","work_id":"a2c11db8-fab0-4877-9fa5-6c90aff97680","year":2020},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:1dcd0733d245cb696cca17ee1821c2f3325eaab34c0b6d6a8fffba721debd634","observation_id":"f2263870-3ce2-4e2c-a3a4-1ee979739682","resolution":{"observed_at":"2026-07-01T07:55:30.296561Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/29.1.308","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"dbSNP: the NCBI database of genetic variation.Nucleic Acids Research, 29(1):308–311, 2001","venue":"Nucleic Acids Research","work_id":"dc0d12d7-e575-4d2b-a01f-1a98b251d805","year":2001},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:af88d6422a815b3b527fc8ea61da642ad6937040864728b09a0e4a04a598f0ae","observation_id":"af453ed8-14b5-4c3b-ab30-586d8d60a7e4","resolution":{"observed_at":"2026-07-01T07:55:30.309641Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gky1015","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Cosmic: the catalogue of somatic mutations in cancer.Nucleic Acids Re- search, 47(D1):D941–D947","venue":"Nucleic Acids Research","work_id":"acb9fc10-8b26-4a3d-a699-9cb9d9fe90c7","year":2019},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:0dd2020b276ba3c628097d6985ec5d4f062e37898070a1f3ca12d39df62099af","observation_id":"39118bc0-b694-4b11-b83c-d8efa9707d37","resolution":{"observed_at":"2026-07-01T07:55:30.312306Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gkae1142","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CZ CELLxGENE Discover: A single-cell data platform for scalable exploration, analysis and modeling of aggregated data.Nucleic Acids Research, 53(D1):D886–D900, 2025","venue":"Nucleic Acids Research","work_id":"64877e09-1b49-4754-8b34-4302c327873e","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:b25b49912eac568e9eb02f273432418bb201cf1211b68de1bb0a4c4a57a275b3","observation_id":"17f97da7-0fc6-4a01-a033-2f712d6b3df1","resolution":{"observed_at":"2026-07-01T07:55:30.323512Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gkac1046","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The next- generation Open Targets Platform: reimagined, redesigned, rebuilt.Nucleic Acids Research, 51 (D1):D1353–D1359, 2023","venue":"Nucleic Acids Research","work_id":"ea0e2bad-ed84-4d01-8008-fc9daeb52e82","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:77fda7f4cc19ee68ad6634dc8bc81034a8296381738e803d4945645d263c4c88","observation_id":"ef7371fc-0ffd-4745-ab49-af9da96d986f","resolution":{"observed_at":"2026-07-01T07:55:30.297363Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.666257Z","title":"Chembl: a large-scale bioactivity database for drug discovery.Nucleic acids research, 40(D1):D1100– D1107","venue":null,"work_id":"fb983880-2b23-49af-a994-f7a03632dcbb","year":2012},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:08520592d4980d775e4f28708e1b9d6adbd7db6e7833397f646d2b6911e10d11","observation_id":"273b911b-1949-4021-840b-a863b1963cee","resolution":{"observed_at":"2026-07-06T14:32:35.667864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gkac1052","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"https://doi.org/10.1093/nar/gkac1052","venue":"Nucleic Acids Research","work_id":"6b69821b-6cac-4133-a008-766466205b52","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:833a818444e0d7ba9add1d07de6b1c3213939e167e090a4d86205ce2a4e0fc11","observation_id":"d644805d-a49c-4ce4-b891-a9688790ff7e","resolution":{"observed_at":"2026-07-01T07:55:30.288407Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-18T07:51:10.659853+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T07:51:10.659853+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T02:37:33.993780Z","title":"KEGG as a reference resource for gene and protein annotation","venue":null,"work_id":"3cb3193c-08f6-47b2-a6ed-187b8edc3bfe","year":2016},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c4717edc8cb9247b3b9f9fa828cd58cfefa9f53cf78121a143a754767e0ca16c","observation_id":"3921d0a8-9247-49cb-b915-025c85957f6b","resolution":{"observed_at":"2026-07-01T07:55:30.288618Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/genetics/iyad031","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"https://doi.org/10.1093/GENETICS/IYAD031 [Wang2022] Wang, J","venue":"Genetics","work_id":"b8f93278-cf88-4390-93bd-d389da071bc0","year":2023},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:737e23dc30bd9f05cf3b84075635a21e327067bfe8f7bf0a6fb23798c64d3693","observation_id":"bf264506-d2d5-4e3b-a1d1-5641d988beb8","resolution":{"observed_at":"2026-07-01T07:55:30.306594Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-11T17:19:25.555506+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T17:19:25.555506+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/nar/gkae1113","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The string database in 2025: protein networks with directional- ity of regulation.Nucleic Acids Research, 53(D1):D730–D737, 01 2025","venue":"Nucleic Acids Research","work_id":"780edbd7-e0ad-4f5b-a80d-4042adb8d2cd","year":2025},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:f3509da31fed1973aa0cfc5c84a4907b198eaa75e7d06dfa8f24c34a91c6510e","observation_id":"3d4a9903-cb1b-4fca-8a0c-cdf575108c3b","resolution":{"observed_at":"2026-07-01T07:55:30.294209Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-11T09:19:18.473653+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T09:19:18.473653+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.735066Z","title":"A large- scale evaluation of computational protein function prediction.Nature Methods, 10(3):221–227,","venue":null,"work_id":"cde82670-b899-453b-8e27-828dc681df07","year":null},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c6f51d57256f7828bcc9cea711f56880d592dc43ebfda4e2fb4704e2f4dd0d99","observation_id":"e2d9e3a3-3369-4b5f-ab7d-083f34ff6684","resolution":{"observed_at":"2026-07-06T14:32:35.736457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/nmeth.2340","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Radivojac, W","venue":"Nature Methods","work_id":"60c73799-c714-4a1f-9427-9700787dc8dd","year":2013},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:9728578e8bb0025f6784dfc7b68c2dd6226d3ff85b3bc85313bbea03d9352e81","observation_id":"26c048d7-6c17-47d1-9959-9040faa5fdc1","resolution":{"observed_at":"2026-07-01T07:55:30.317566Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1186/s13059-019-1835-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.Genome Biology, 20(1):244, 2019","venue":"Genome biology","work_id":"9ff75682-0d52-440f-82af-314eb60be28c","year":2019},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:74bdbd5052011798fb2d4c975bafff0e9709917f49b2a9ef9fafde405450020b","observation_id":"7409f7f7-5c56-4a03-a430-4f261268a635","resolution":{"observed_at":"2026-07-01T07:55:30.314880Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.732843Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"c9e36205-5593-4918-bef8-197be31857f6","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:2174f964b21bbf0d48f96b1f6f88c5a45bdba207de23d05588e5e2940e38ab2a","observation_id":"42bf3a2b-530c-4da0-8dd5-8b4bf6340fa6","resolution":{"observed_at":"2026-07-06T14:32:35.733959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.830527Z","title":"The FineWeb datasets: Decanting the web for the finest text data at scale","venue":null,"work_id":"0785e3a0-a2ac-42ac-b999-24b0985ac9f7","year":2024},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:2af19067cdc4d1f1ffd008391ea85df2258c6993c9d3fdf85fa96e1377fd68d4","observation_id":"cf4bb96a-a23a-4321-8eb2-e42a7f97fc96","resolution":{"observed_at":"2026-07-06T14:32:35.831567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-09T19:36:29.521451Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"139a920c-85a1-42e5-937e-f14d907436d5","year":2019},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:70bf78bbac7f12bc6c498332f578030a216d1d5943dd4d1eef206b01746bc110","observation_id":"177e83bb-cff7-4add-8ddc-df7faeb7258d","resolution":{"observed_at":"2026-07-06T14:32:35.754590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1405.2020","last_updated":"2014-05-08T17:04:15Z","snapshot_observed_at":"2026-08-04T16:50:32.529025Z","submitted_at":"2014-05-08T17:04:15Z","title":"Generalized Slow Roll for Tensors","version":1},"cited_work":{"arxiv_id":"1405.2020","doi":"10.1109/sc41405.2020","metadata_source":"pith","pith_arxiv_id":"1405.2020","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Generalized Slow Roll for Tensors","venue":"astro-ph.CO","work_id":"32348cef-09e4-43f2-b53c-d785fa1937a5","year":2014},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/1405.2020","citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:9c53c7dc0843562ac21c201a92b8af37fefc73f2c7e2184ba6354ae24998388a","observation_id":"83939c43-0804-4ef7-88d2-5e19336b0378","resolution":{"observed_at":"2026-07-01T07:55:30.303997Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-14T13:50:02.178338+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T13:50:02.178338+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-06T14:32:35.787905Z","title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","venue":null,"work_id":"f8d9974b-bc8a-45f4-bbbb-93241c55a25d","year":2022},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:f93e9f2e3383c568d2de0506bf87c2233fc8998bf12a5c987e767288e87923ba","observation_id":"1954ad8b-bf53-4fb5-a941-c065afc68a79","resolution":{"observed_at":"2026-07-06T14:32:35.789021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2460.83160","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-01T07:55:31.034634Z","title":"warm→cos","venue":null,"work_id":"3715aaec-dbde-43e3-a289-211835e2a099","year":2017},"citing_paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-07-01T07:48:31.110861Z"},"links":{"citing_paper":"/paper/2606.16517"},"observation_digest":"sha256:c49e63033556ebfdf7d676bb1707839ef4d6417cae831bdac4c4f55c756e0517","observation_id":"3bee5b8b-92cf-4123-aee4-806b448a2e5a","resolution":{"observed_at":"2026-07-01T07:55:31.036741Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2606.16517","last_updated":"2026-06-30T13:49:08Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:52:37.922109Z","submitted_at":"2026-06-15T10:19:49Z","title":"How Post-Training Shapes Biological Reasoning Models"},"reference_resolution":{"displayed":99,"state_counts":{"malformed_identifier":1,"metadata_mismatch":5,"parse_uncertain":0,"unresolved":3,"verified_exact":22,"verified_fuzzy":68},"total_outbound_references":99},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 99 of 99 outbound references and 0 inbound Pith citation observations for arXiv:2606.16517."}