{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3HKYS33U4HKCQKLA67ZK55NW2R","short_pith_number":"pith:3HKYS33U","schema_version":"1.0","canonical_sha256":"d9d5896f74e1d4282960f7f2aef5b6d45734b2a2c6918941b5314ad35ce45e76","source":{"kind":"arxiv","id":"2402.04997","version":2},"attestation_state":"computed","paper":{"title":"Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"stat.ML","authors_text":"Andrew Campbell, Jason Yim, Regina Barzilay, Tommi Jaakkola, Tom Rainforth","submitted_at":"2024-02-07T16:15:36Z","abstract_excerpt":"Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models to be applied to multimodal continuous and discrete data problems. Our key insight is that the discrete equivalent of continuous space flow matching can be realized using Continuous Time Markov Chains. DFMs benefit from a simple derivation that includes discrete diffusion models as a specific instance while allowing improved performance over existing diffus"},"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":"2402.04997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-07T16:15:36Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"460e1346dedee44728393ed7b2cd2355ae14eccceb3beedb8c22538aec7579c7","abstract_canon_sha256":"b5e0e430d016823bc983cac2c0ab1cf8cedd02cb55ef2e37c8d9af556b443ea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:05.690465Z","signature_b64":"TCReTJV9t3+rsj+kaBeU8k0tXXyq58yQV/NTqhUuD1QLNKW4JhclzEzkMeEt6F7lTEyXF1KccszWpjmYlh5aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9d5896f74e1d4282960f7f2aef5b6d45734b2a2c6918941b5314ad35ce45e76","last_reissued_at":"2026-07-05T08:28:05.690000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:05.690000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"stat.ML","authors_text":"Andrew Campbell, Jason Yim, Regina Barzilay, Tommi Jaakkola, Tom Rainforth","submitted_at":"2024-02-07T16:15:36Z","abstract_excerpt":"Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models to be applied to multimodal continuous and discrete data problems. Our key insight is that the discrete equivalent of continuous space flow matching can be realized using Continuous Time Markov Chains. DFMs benefit from a simple derivation that includes discrete diffusion models as a specific instance while allowing improved performance over existing diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04997","kind":"arxiv","version":2},"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/2402.04997/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":"2402.04997","created_at":"2026-07-05T08:28:05.690056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04997v2","created_at":"2026-07-05T08:28:05.690056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04997","created_at":"2026-07-05T08:28:05.690056+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HKYS33U4HKC","created_at":"2026-07-05T08:28:05.690056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HKYS33U4HKCQKLA","created_at":"2026-07-05T08:28:05.690056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HKYS33U","created_at":"2026-07-05T08:28:05.690056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10543","citing_title":"Flexible Flows for Biological Sequence Design","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08417","citing_title":"Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10618","citing_title":"D-Flow: Multi-modality Flow Matching for D-peptide Design","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":293,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22765","citing_title":"Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04883","citing_title":"Protein Autoregressive Modeling via Multiscale Structure Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21485","citing_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16755","citing_title":"Learning Unbiased Permutations via Flow Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03206","citing_title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03360","citing_title":"A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26841","citing_title":"Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09981","citing_title":"Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00948","citing_title":"Co-Generative De Novo Functional Protein Design","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16232","citing_title":"Neuro-Symbolic ODE Discovery with Latent Grammar Flow","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17310","citing_title":"Interpolating Discrete Diffusion Models with Controllable Resampling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04119","citing_title":"Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R","json":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R.json","graph_json":"https://pith.science/api/pith-number/3HKYS33U4HKCQKLA67ZK55NW2R/graph.json","events_json":"https://pith.science/api/pith-number/3HKYS33U4HKCQKLA67ZK55NW2R/events.json","paper":"https://pith.science/paper/3HKYS33U"},"agent_actions":{"view_html":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R","download_json":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R.json","view_paper":"https://pith.science/paper/3HKYS33U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04997&json=true","fetch_graph":"https://pith.science/api/pith-number/3HKYS33U4HKCQKLA67ZK55NW2R/graph.json","fetch_events":"https://pith.science/api/pith-number/3HKYS33U4HKCQKLA67ZK55NW2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R/action/storage_attestation","attest_author":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R/action/author_attestation","sign_citation":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R/action/citation_signature","submit_replication":"https://pith.science/pith/3HKYS33U4HKCQKLA67ZK55NW2R/action/replication_record"}},"created_at":"2026-07-05T08:28:05.690056+00:00","updated_at":"2026-07-05T08:28:05.690056+00:00"}