{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BC5TGPQW27WYPS5VBXLYRI7QQS","short_pith_number":"pith:BC5TGPQW","schema_version":"1.0","canonical_sha256":"08bb333e16d7ed87cbb50dd788a3f0848f918e14201cb9d1de0452fe8c410eb8","source":{"kind":"arxiv","id":"2308.07037","version":6},"attestation_state":"computed","paper":{"title":"Bayesian Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Faustino Gomez, Rupesh Kumar Srivastava, Timothy Atkinson","submitted_at":"2023-08-14T09:56:35Z","abstract_excerpt":"This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference in the light of noisy data samples, then passed as input to a neural network that outputs a second, interdependent distribution. Starting from a simple prior and iteratively updating the two distributions yields a generative procedure similar to the reverse process of diffusion models; however it is conceptually simpler in that no forward process is required. Discrete and continuous-time loss functions are derive"},"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":"2308.07037","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-14T09:56:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"416711cb4e90cb85de78456e99b4098ceae23b347dc4f51edcbdf0fd33a063da","abstract_canon_sha256":"e9d54d08dac77ea0f9d67731470a67cbbca878149099e676037896a6725d2931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:11.940990Z","signature_b64":"XapSS46hRJc2aetgPbhjO6z5IpK0EZRgGElfjUIEeQAnBt46Rrxe6MBwdR+XNZSS3ITzdZT8R8jWEt9p3Sb3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08bb333e16d7ed87cbb50dd788a3f0848f918e14201cb9d1de0452fe8c410eb8","last_reissued_at":"2026-07-05T10:28:11.940478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:11.940478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Faustino Gomez, Rupesh Kumar Srivastava, Timothy Atkinson","submitted_at":"2023-08-14T09:56:35Z","abstract_excerpt":"This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference in the light of noisy data samples, then passed as input to a neural network that outputs a second, interdependent distribution. Starting from a simple prior and iteratively updating the two distributions yields a generative procedure similar to the reverse process of diffusion models; however it is conceptually simpler in that no forward process is required. Discrete and continuous-time loss functions are derive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07037","kind":"arxiv","version":6},"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/2308.07037/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":"2308.07037","created_at":"2026-07-05T10:28:11.940541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07037v6","created_at":"2026-07-05T10:28:11.940541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07037","created_at":"2026-07-05T10:28:11.940541+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC5TGPQW27WY","created_at":"2026-07-05T10:28:11.940541+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC5TGPQW27WYPS5V","created_at":"2026-07-05T10:28:11.940541+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC5TGPQW","created_at":"2026-07-05T10:28:11.940541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01628","citing_title":"Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19726","citing_title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16818","citing_title":"Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2508.02193","citing_title":"Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":236,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS","json":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS.json","graph_json":"https://pith.science/api/pith-number/BC5TGPQW27WYPS5VBXLYRI7QQS/graph.json","events_json":"https://pith.science/api/pith-number/BC5TGPQW27WYPS5VBXLYRI7QQS/events.json","paper":"https://pith.science/paper/BC5TGPQW"},"agent_actions":{"view_html":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS","download_json":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS.json","view_paper":"https://pith.science/paper/BC5TGPQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07037&json=true","fetch_graph":"https://pith.science/api/pith-number/BC5TGPQW27WYPS5VBXLYRI7QQS/graph.json","fetch_events":"https://pith.science/api/pith-number/BC5TGPQW27WYPS5VBXLYRI7QQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS/action/storage_attestation","attest_author":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS/action/author_attestation","sign_citation":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS/action/citation_signature","submit_replication":"https://pith.science/pith/BC5TGPQW27WYPS5VBXLYRI7QQS/action/replication_record"}},"created_at":"2026-07-05T10:28:11.940541+00:00","updated_at":"2026-07-05T10:28:11.940541+00:00"}