{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CPZG773HB24XEDGWTWT4KCSKTV","short_pith_number":"pith:CPZG773H","schema_version":"1.0","canonical_sha256":"13f26fff670eb9720cd69da7c50a4a9d7856e9cf6e2cb9eda01f41237e6b0189","source":{"kind":"arxiv","id":"2606.27752","version":1},"attestation_state":"computed","paper":{"title":"PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anurendra Kumar, Dongxia Wu, Emily B. Fox, Emma Lundberg, Mingyu Li, Serena Yeung-Levy, Yuhui Zhang","submitted_at":"2026-06-26T06:15:04Z","abstract_excerpt":"Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. While recent generative models improve population-level prediction, individual generated cells are not explicitly checked for biological consistency. We introduce PerturbCellRL, a reinforcement learning (RL) framework that post-trains a pretrained single-cell transcriptomic generator using a suite of cell-level verifiers as rewards. These verifiers define four rewards: Pearson top-k similarity, RMSE top-k proximity, DE Spearman, and Pathway activity. The Pathw"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"73514c782c94355ad427f3fff462e22832de992b089c296ee07bea2f723fbed2","abstract_canon_sha256":"f4bb0d97db6919fc77f14b0a2489a769edc80cbf24e252d2024901dd40e53b1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:47.464348Z","signature_b64":"CLigmxWELpaIUNAVycO7c4Du+WTIMRXzuqh+kFJTmvZcPBDj9pQO+myd4FtJvQddlSNGgTbO5JnjWW9UID9pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f26fff670eb9720cd69da7c50a4a9d7856e9cf6e2cb9eda01f41237e6b0189","last_reissued_at":"2026-06-29T01:14:47.463942Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:47.463942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anurendra Kumar, Dongxia Wu, Emily B. Fox, Emma Lundberg, Mingyu Li, Serena Yeung-Levy, Yuhui Zhang","submitted_at":"2026-06-26T06:15:04Z","abstract_excerpt":"Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. While recent generative models improve population-level prediction, individual generated cells are not explicitly checked for biological consistency. We introduce PerturbCellRL, a reinforcement learning (RL) framework that post-trains a pretrained single-cell transcriptomic generator using a suite of cell-level verifiers as rewards. These verifiers define four rewards: Pearson top-k similarity, RMSE top-k proximity, DE Spearman, and Pathway activity. The Pathw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27752","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.27752/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27752","created_at":"2026-06-29T01:14:47.464000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27752v1","created_at":"2026-06-29T01:14:47.464000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27752","created_at":"2026-06-29T01:14:47.464000+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPZG773HB24X","created_at":"2026-06-29T01:14:47.464000+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPZG773HB24XEDGW","created_at":"2026-06-29T01:14:47.464000+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPZG773H","created_at":"2026-06-29T01:14:47.464000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV","json":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV.json","graph_json":"https://pith.science/api/pith-number/CPZG773HB24XEDGWTWT4KCSKTV/graph.json","events_json":"https://pith.science/api/pith-number/CPZG773HB24XEDGWTWT4KCSKTV/events.json","paper":"https://pith.science/paper/CPZG773H"},"agent_actions":{"view_html":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV","download_json":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV.json","view_paper":"https://pith.science/paper/CPZG773H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27752&json=true","fetch_graph":"https://pith.science/api/pith-number/CPZG773HB24XEDGWTWT4KCSKTV/graph.json","fetch_events":"https://pith.science/api/pith-number/CPZG773HB24XEDGWTWT4KCSKTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV/action/storage_attestation","attest_author":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV/action/author_attestation","sign_citation":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV/action/citation_signature","submit_replication":"https://pith.science/pith/CPZG773HB24XEDGWTWT4KCSKTV/action/replication_record"}},"created_at":"2026-06-29T01:14:47.464000+00:00","updated_at":"2026-06-29T01:14:47.464000+00:00"}