{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AYJA3I6G4TF6ERM6K7OIHCZUX7","short_pith_number":"pith:AYJA3I6G","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"},"canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","source":{"kind":"arxiv","id":"2603.21743","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21743","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21743v4","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21743","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"AYJA3I6G4TF6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"AYJA3I6G4TF6ERM6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"AYJA3I6G","created_at":"2026-05-22T01:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AYJA3I6G4TF6ERM6K7OIHCZUX7","target":"record","payload":{"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"},"canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","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"},"source_kind":"arxiv","source_id":"2603.21743","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXekbnumGKbWmsPOIyIDdP7elYKOUU/RpfczWCxHRiPX9IlPGjCPLSPUdYCnn7EhVXuK3K5FWa3IOmeL/8JQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:52:52.288658Z"},"content_sha256":"b2cbff52ba03da15b43663f6f1b8a28ddeaa4a06ae3ab493ec0450aa77c5b401","schema_version":"1.0","event_id":"sha256:b2cbff52ba03da15b43663f6f1b8a28ddeaa4a06ae3ab493ec0450aa77c5b401"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AYJA3I6G4TF6ERM6K7OIHCZUX7","target":"graph","payload":{"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"},"verdict_id":"bb411121-dfa1-4da1-9cee-c48a8b514e64"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bu3srlOEHlfDOybzYijRJ04gtAceZISPrAGlPPpoTysnhuqgr01/asi+wTFVBPhVSCcKAK6O/UuzyvZ3g77cBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:52:52.289296Z"},"content_sha256":"cb2cf911410343384d34a6592ecb1505c20029498a04a74444b17d1910dd7b7d","schema_version":"1.0","event_id":"sha256:cb2cf911410343384d34a6592ecb1505c20029498a04a74444b17d1910dd7b7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/bundle.json","state_url":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T06:52:52Z","links":{"resolver":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7","bundle":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/bundle.json","state":"https://pith.science/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AYJA3I6G4TF6ERM6K7OIHCZUX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AYJA3I6G4TF6ERM6K7OIHCZUX7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"028703b9a3764f2b820b079fef07310045ac9e7bb4a525fc7b317459e67392db","cross_cats_sorted":["q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:33:18Z","title_canon_sha256":"b3eac08c29a709d337e3e547cb42778e2acb8df80ccda2fe773dfaf5dbb9eb4f"},"schema_version":"1.0","source":{"id":"2603.21743","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21743","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21743v4","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21743","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"AYJA3I6G4TF6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"AYJA3I6G4TF6ERM6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"AYJA3I6G","created_at":"2026-05-22T01:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:cb2cf911410343384d34a6592ecb1505c20029498a04a74444b17d1910dd7b7d","target":"graph","created_at":"2026-05-22T01:03:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules."}],"snapshot_sha256":"be02fedcba7bdd0c01dc9680bedeb8104529a9d947c899f806edcfc4690dc368"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.21743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongxia Wu, Elaine Sui, Emily B. Fox, Emma Lundberg, Serena Yeung-Levy, Shiye Su, Yuhui Zhang","cross_cats":["q-bio.QM"],"headline":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:33:18Z","title":"CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21743","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T01:01:16.403684Z","id":"bb411121-dfa1-4da1-9cee-c48a8b514e64","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Reinforcement learning post-training with biological rewards improves virtual cell generators to respect physical and biological rules.","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.","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."}},"verdict_id":"bb411121-dfa1-4da1-9cee-c48a8b514e64"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2cbff52ba03da15b43663f6f1b8a28ddeaa4a06ae3ab493ec0450aa77c5b401","target":"record","created_at":"2026-05-22T01:03:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"028703b9a3764f2b820b079fef07310045ac9e7bb4a525fc7b317459e67392db","cross_cats_sorted":["q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:33:18Z","title_canon_sha256":"b3eac08c29a709d337e3e547cb42778e2acb8df80ccda2fe773dfaf5dbb9eb4f"},"schema_version":"1.0","source":{"id":"2603.21743","kind":"arxiv","version":4}},"canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06120da3c6e4cbe2459e57dc838b34bfdc31b25819a3f25c5d243b3f206600c3","first_computed_at":"2026-05-22T01:03:18.898926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:18.898926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"grzg1NeK617xohLtFWLVj3/9AzYPRHGob9d0loDoEhsgaOpyZmcfB+6OtqBX79tVUbtzHpXYfKjVdda3jalqCA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:18.899748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.21743","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2cbff52ba03da15b43663f6f1b8a28ddeaa4a06ae3ab493ec0450aa77c5b401","sha256:cb2cf911410343384d34a6592ecb1505c20029498a04a74444b17d1910dd7b7d"],"state_sha256":"63c63902cb99fd31c8c8ce1dad761d2043180c305f9ecd372bd5c891813dbf1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8BYL+VF1+xHzedb+oZwOargSGUjkyWDBk3luu1U5jY/XEXLWiubnL0t04RN17rxQIaE5bcUHsjXEhBEUZ5XqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:52:52.294828Z","bundle_sha256":"df5ab9104a0c01a307202509042b7fab412805d0436f715fb003074ea5733c93"}}