{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AYJA3I6G4TF6ERM6K7OIHCZUX7","short_pith_number":"pith:AYJA3I6G","schema_version":"1.0","canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","source":{"kind":"arxiv","id":"2603.21743","version":4},"attestation_state":"computed","paper":{"title":"CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules.","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dongxia Wu, Elaine Sui, Emily B. Fox, Emma Lundberg, Serena Yeung-Levy, Shiye Su, Yuhui Zhang","submitted_at":"2026-03-23T09:33:18Z","abstract_excerpt":"Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the st"},"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":"2603.21743","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:33:18Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"b3eac08c29a709d337e3e547cb42778e2acb8df80ccda2fe773dfaf5dbb9eb4f","abstract_canon_sha256":"028703b9a3764f2b820b079fef07310045ac9e7bb4a525fc7b317459e67392db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:18.899748Z","signature_b64":"grzg1NeK617xohLtFWLVj3/9AzYPRHGob9d0loDoEhsgaOpyZmcfB+6OtqBX79tVUbtzHpXYfKjVdda3jalqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","last_reissued_at":"2026-05-22T01:03:18.898926Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:18.898926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules.","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dongxia Wu, Elaine Sui, Emily B. Fox, Emma Lundberg, Serena Yeung-Levy, Shiye Su, Yuhui Zhang","submitted_at":"2026-03-23T09:33:18Z","abstract_excerpt":"Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the st"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling, advancing beyond visually realistic generations towards biologically meaningful ones.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The seven reward functions accurately capture biologically meaningful constraints without introducing unintended biases or allowing the model to game the rewards while still violating real cellular physics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CellFluxRL post-trains the CellFlux generative model with reinforcement learning driven by biologically meaningful reward functions, yielding virtual cell images that better satisfy physical and biological constraints than the base model.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"be02fedcba7bdd0c01dc9680bedeb8104529a9d947c899f806edcfc4690dc368"},"source":{"id":"2603.21743","kind":"arxiv","version":4},"verdict":{"id":"bb411121-dfa1-4da1-9cee-c48a8b514e64","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:01:16.403684Z","strongest_claim":"CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling, advancing beyond visually realistic generations towards biologically meaningful ones.","one_line_summary":"CellFluxRL post-trains the CellFlux generative model with reinforcement learning driven by biologically meaningful reward functions, yielding virtual cell images that better satisfy physical and biological constraints than the base model.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The seven reward functions accurately capture biologically meaningful constraints without introducing unintended biases or allowing the model to game the rewards while still violating real cellular physics.","pith_extraction_headline":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.21743/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":"2603.21743","created_at":"2026-05-22T01:03:18.899012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.21743v4","created_at":"2026-05-22T01:03:18.899012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21743","created_at":"2026-05-22T01:03:18.899012+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYJA3I6G4TF6","created_at":"2026-05-22T01:03:18.899012+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYJA3I6G4TF6ERM6","created_at":"2026-05-22T01:03:18.899012+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYJA3I6G","created_at":"2026-05-22T01:03:18.899012+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/AYJA3I6G4TF6ERM6K7OIHCZUX7","json":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7.json","graph_json":"https://pith.science/api/pith-number/AYJA3I6G4TF6ERM6K7OIHCZUX7/graph.json","events_json":"https://pith.science/api/pith-number/AYJA3I6G4TF6ERM6K7OIHCZUX7/events.json","paper":"https://pith.science/paper/AYJA3I6G"},"agent_actions":{"view_html":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7","download_json":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7.json","view_paper":"https://pith.science/paper/AYJA3I6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.21743&json=true","fetch_graph":"https://pith.science/api/pith-number/AYJA3I6G4TF6ERM6K7OIHCZUX7/graph.json","fetch_events":"https://pith.science/api/pith-number/AYJA3I6G4TF6ERM6K7OIHCZUX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/action/storage_attestation","attest_author":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/action/author_attestation","sign_citation":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/action/citation_signature","submit_replication":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/action/replication_record"}},"created_at":"2026-05-22T01:03:18.899012+00:00","updated_at":"2026-05-22T01:03:18.899012+00:00"}