{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ATQXUNDXBO2XDNKBYKOGN6WXS","short_pith_number":"pith:4ATQXUND","schema_version":"1.0","canonical_sha256":"e0270bd1a3b85dab8daa0e14e337d6bc8f4040223e00e2862ecb5a57a3ba03de","source":{"kind":"arxiv","id":"2305.16860","version":2},"attestation_state":"computed","paper":{"title":"Error Bounds for Flow Matching Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arnaud Doucet, George Deligiannidis, Joe Benton","submitted_at":"2023-05-26T12:13:53Z","abstract_excerpt":"Score-based generative models are a popular class of generative modelling techniques relying on stochastic differential equations (SDE). From their inception, it was realized that it was also possible to perform generation using ordinary differential equations (ODE) rather than SDE. This led to the introduction of the probability flow ODE approach and denoising diffusion implicit models. Flow matching methods have recently further extended these ODE-based approaches and approximate a flow between two arbitrary probability distributions. Previous work derived bounds on the approximation error o"},"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":"2305.16860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T12:13:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd66364fab0de1ba2ffe73467ddbb8b51222b0f929f10f787c799347ab2f72ad","abstract_canon_sha256":"c31e035becd93c52316218bf7eb47cd2d44e2cafd68b9bbbdf28006e11f1e47d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:53.015555Z","signature_b64":"3G3QPTqpaIZheEcBvCjcDz3BQspmeoJGbfY+YRNGYBEsjhOhSIhKNFnYdhsRPFKi8srk4H+5uya82BifurIkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0270bd1a3b85dab8daa0e14e337d6bc8f4040223e00e2862ecb5a57a3ba03de","last_reissued_at":"2026-07-05T07:43:53.015161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:53.015161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Bounds for Flow Matching Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arnaud Doucet, George Deligiannidis, Joe Benton","submitted_at":"2023-05-26T12:13:53Z","abstract_excerpt":"Score-based generative models are a popular class of generative modelling techniques relying on stochastic differential equations (SDE). From their inception, it was realized that it was also possible to perform generation using ordinary differential equations (ODE) rather than SDE. This led to the introduction of the probability flow ODE approach and denoising diffusion implicit models. Flow matching methods have recently further extended these ODE-based approaches and approximate a flow between two arbitrary probability distributions. Previous work derived bounds on the approximation error o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16860","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/2305.16860/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":"2305.16860","created_at":"2026-07-05T07:43:53.015217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16860v2","created_at":"2026-07-05T07:43:53.015217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16860","created_at":"2026-07-05T07:43:53.015217+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ATQXUNDXBO2","created_at":"2026-07-05T07:43:53.015217+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ATQXUNDXBO2XDNK","created_at":"2026-07-05T07:43:53.015217+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ATQXUND","created_at":"2026-07-05T07:43:53.015217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23920","citing_title":"Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13400","citing_title":"PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11138","citing_title":"First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07271","citing_title":"Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27608","citing_title":"Qwen-Image-2.0-RL Technical Report","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08398","citing_title":"Exploring and Exploiting Stability in Latent Flow Matching","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08398","citing_title":"Exploring and Exploiting Stability in Latent Flow Matching","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10857","citing_title":"Query Lower Bounds for Diffusion Sampling","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06680","citing_title":"On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06065","citing_title":"Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS","json":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS.json","graph_json":"https://pith.science/api/pith-number/4ATQXUNDXBO2XDNKBYKOGN6WXS/graph.json","events_json":"https://pith.science/api/pith-number/4ATQXUNDXBO2XDNKBYKOGN6WXS/events.json","paper":"https://pith.science/paper/4ATQXUND"},"agent_actions":{"view_html":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS","download_json":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS.json","view_paper":"https://pith.science/paper/4ATQXUND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16860&json=true","fetch_graph":"https://pith.science/api/pith-number/4ATQXUNDXBO2XDNKBYKOGN6WXS/graph.json","fetch_events":"https://pith.science/api/pith-number/4ATQXUNDXBO2XDNKBYKOGN6WXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS/action/storage_attestation","attest_author":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS/action/author_attestation","sign_citation":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS/action/citation_signature","submit_replication":"https://pith.science/pith/4ATQXUNDXBO2XDNKBYKOGN6WXS/action/replication_record"}},"created_at":"2026-07-05T07:43:53.015217+00:00","updated_at":"2026-07-05T07:43:53.015217+00:00"}