{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I33NTXR426DT44ZDYO5AKMVDTJ","short_pith_number":"pith:I33NTXR4","canonical_record":{"source":{"id":"2512.10857","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-11T17:53:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"31a7b1cdbc63c2ed2a0f561d652afcbf560723f14f3d56370f77f22804d202b2","abstract_canon_sha256":"0de2b24aeb2a13a3f40cd519c3612eac774ee91b86147128a9b00cef846b768c"},"schema_version":"1.0"},"canonical_sha256":"46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e","source":{"kind":"arxiv","id":"2512.10857","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10857","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10857v2","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10857","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"I33NTXR426DT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"I33NTXR426DT44ZD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"I33NTXR4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I33NTXR426DT44ZDYO5AKMVDTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2512.10857","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-11T17:53:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"31a7b1cdbc63c2ed2a0f561d652afcbf560723f14f3d56370f77f22804d202b2","abstract_canon_sha256":"0de2b24aeb2a13a3f40cd519c3612eac774ee91b86147128a9b00cef846b768c"},"schema_version":"1.0"},"canonical_sha256":"46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:32.682812Z","signature_b64":"5bgz0wE90noSTbNf+eLOA1nJGSHbX0kNVbQoGwloFhf+kvAV71mQ6numsILtpthBTOvUW5HZIIpqTOAcBX3JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e","last_reissued_at":"2026-05-18T03:09:32.682284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:32.682284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.10857","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xrmi0C6xl+AtDluOMHPQHo9hsG5LgxmjzTICrbAqA4JpXyNuTOehmKqZ+lBcY7jqwoKiQAR3eF9FhNSmfzAoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:12:13.910409Z"},"content_sha256":"15c6977ad1ab274ecec36622b57951197744a1b0e24b682aadbfca316f871fdb","schema_version":"1.0","event_id":"sha256:15c6977ad1ab274ecec36622b57951197744a1b0e24b682aadbfca316f871fdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I33NTXR426DT44ZDYO5AKMVDTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chirag Modi, Eric Vanden-Eijnden, Jiequn Han, Joan Bruna","submitted_at":"2025-12-11T17:53:38Z","abstract_excerpt":"Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A generative model for the original data thus requires solving an inverse problem at the level of distributions. In this work, we introduce a novel approach to this task based on Stochastic Interpolants: we iteratively update a transport map between corrupted and clean data samples using only access to t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The iterative procedure converges to the desired self-consistent transport map under appropriate (unspecified in abstract) conditions on the corruption channel and data distributions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"274414270b7fcb0cb953207e90a878712024d0a68875a54d0b076c2cb2257fd7"},"source":{"id":"2512.10857","kind":"arxiv","version":2},"verdict":{"id":"e2f790ff-9258-4801-b297-32b50b68459d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T22:59:02.873512Z","strongest_claim":"Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data.","one_line_summary":"SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The iterative procedure converges to the desired self-consistent transport map under appropriate (unspecified in abstract) conditions on the corruption channel and data distributions.","pith_extraction_headline":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone."},"references":{"count":18,"sample":[{"doi":"","year":null,"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","ref_index":1,"cited_arxiv_id":"2303.08797","is_internal_anchor":true},{"doi":"","year":null,"title":"Stochastic interpolants with data-dependent couplings.arXiv preprint arXiv:2310.03725,","work_id":"9d29254d-1e1b-42c3-ac06-35e6ef5d5d16","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Building normalizing flows with stochastic interpolants","work_id":"85ffbc5d-05cf-43b9-88b7-94664bc37be4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Nearlyd-linear convergence bounds for diffusion models via stochastic local- ization.CoRR, abs/2308.03686","work_id":"c042e9f5-74ae-4fea-b435-c2920ccb9e2e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2209.11215 , year =","work_id":"311398cb-1dd2-4542-88ad-c173f1545e4a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"127863a653e86cbe91bfb68002d676a9c7d9f0c38368d7375417b13848c1ab9b","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b639b8e8390900e35dcda75dd5ccfced9ebc04367101d45e95e4f642d8b5c145"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e2f790ff-9258-4801-b297-32b50b68459d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fobOTvkk4EBp7PLk2ofvRFOZO9+yM+lKCx5PpQfKPwNwX2zR7LXKt2bQ8XWIprsFVnqEvQAL2zGFPonxQwndAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:12:13.910938Z"},"content_sha256":"fdb89bc0cd9e0d33d9e131ae3f5fcaaae59c2863bec26c97ef7082ae35e994ec","schema_version":"1.0","event_id":"sha256:fdb89bc0cd9e0d33d9e131ae3f5fcaaae59c2863bec26c97ef7082ae35e994ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I33NTXR426DT44ZDYO5AKMVDTJ/bundle.json","state_url":"https://pith.science/pith/I33NTXR426DT44ZDYO5AKMVDTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I33NTXR426DT44ZDYO5AKMVDTJ/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":"2026-06-01T17:12:13Z","links":{"resolver":"https://pith.science/pith/I33NTXR426DT44ZDYO5AKMVDTJ","bundle":"https://pith.science/pith/I33NTXR426DT44ZDYO5AKMVDTJ/bundle.json","state":"https://pith.science/pith/I33NTXR426DT44ZDYO5AKMVDTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I33NTXR426DT44ZDYO5AKMVDTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I33NTXR426DT44ZDYO5AKMVDTJ","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":"0de2b24aeb2a13a3f40cd519c3612eac774ee91b86147128a9b00cef846b768c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-11T17:53:38Z","title_canon_sha256":"31a7b1cdbc63c2ed2a0f561d652afcbf560723f14f3d56370f77f22804d202b2"},"schema_version":"1.0","source":{"id":"2512.10857","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10857","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10857v2","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10857","created_at":"2026-05-18T03:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"I33NTXR426DT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"I33NTXR426DT44ZD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"I33NTXR4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fdb89bc0cd9e0d33d9e131ae3f5fcaaae59c2863bec26c97ef7082ae35e994ec","target":"graph","created_at":"2026-05-18T03:09:32Z","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":"Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The iterative procedure converges to the desired self-consistent transport map under appropriate (unspecified in abstract) conditions on the corruption channel and data distributions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone."}],"snapshot_sha256":"274414270b7fcb0cb953207e90a878712024d0a68875a54d0b076c2cb2257fd7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b639b8e8390900e35dcda75dd5ccfced9ebc04367101d45e95e4f642d8b5c145"},"paper":{"abstract_excerpt":"Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A generative model for the original data thus requires solving an inverse problem at the level of distributions. In this work, we introduce a novel approach to this task based on Stochastic Interpolants: we iteratively update a transport map between corrupted and clean data samples using only access to t","authors_text":"Chirag Modi, Eric Vanden-Eijnden, Jiequn Han, Joan Bruna","cross_cats":["cs.AI","stat.ML"],"headline":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-11T17:53:38Z","title":"Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants"},"references":{"count":18,"internal_anchors":2,"resolved_work":18,"sample":[{"cited_arxiv_id":"2303.08797","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Stochastic interpolants with data-dependent couplings.arXiv preprint arXiv:2310.03725,","work_id":"9d29254d-1e1b-42c3-ac06-35e6ef5d5d16","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Building normalizing flows with stochastic interpolants","work_id":"85ffbc5d-05cf-43b9-88b7-94664bc37be4","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Nearlyd-linear convergence bounds for diffusion models via stochastic local- ization.CoRR, abs/2308.03686","work_id":"c042e9f5-74ae-4fea-b435-c2920ccb9e2e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2209.11215 , year =","work_id":"311398cb-1dd2-4542-88ad-c173f1545e4a","year":null}],"snapshot_sha256":"127863a653e86cbe91bfb68002d676a9c7d9f0c38368d7375417b13848c1ab9b"},"source":{"id":"2512.10857","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T22:59:02.873512Z","id":"e2f790ff-9258-4801-b297-32b50b68459d","model_set":{"reader":"grok-4.3"},"one_line_summary":"SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An iterative procedure with stochastic interpolants learns a transport map that inverts black-box corruptions to generate clean data from corrupted observations alone.","strongest_claim":"Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data.","weakest_assumption":"The iterative procedure converges to the desired self-consistent transport map under appropriate (unspecified in abstract) conditions on the corruption channel and data distributions."}},"verdict_id":"e2f790ff-9258-4801-b297-32b50b68459d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:15c6977ad1ab274ecec36622b57951197744a1b0e24b682aadbfca316f871fdb","target":"record","created_at":"2026-05-18T03:09:32Z","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":"0de2b24aeb2a13a3f40cd519c3612eac774ee91b86147128a9b00cef846b768c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-11T17:53:38Z","title_canon_sha256":"31a7b1cdbc63c2ed2a0f561d652afcbf560723f14f3d56370f77f22804d202b2"},"schema_version":"1.0","source":{"id":"2512.10857","kind":"arxiv","version":2}},"canonical_sha256":"46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46f6d9de3cd7873e7323c3ba0532a39a6a058a4ce8ab55f8ac562ca37bbb841e","first_computed_at":"2026-05-18T03:09:32.682284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:32.682284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5bgz0wE90noSTbNf+eLOA1nJGSHbX0kNVbQoGwloFhf+kvAV71mQ6numsILtpthBTOvUW5HZIIpqTOAcBX3JDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:32.682812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10857","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15c6977ad1ab274ecec36622b57951197744a1b0e24b682aadbfca316f871fdb","sha256:fdb89bc0cd9e0d33d9e131ae3f5fcaaae59c2863bec26c97ef7082ae35e994ec"],"state_sha256":"912c2f4db0c30c4d7d751f6d378f0a8b969bca2419035920137fccbfe674d2ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzuSvgIoTUmluLGlIfUXc0Z6vU3/G8G5I+zoIZvLoWkhhXxHScqvT3OKxq8Wtsn1+8TQZH8f7FTndhWwCOfODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:12:13.913540Z","bundle_sha256":"eda19788b81c2f99b0fe5c3bd4b657bbbe67a28e03dca9609e3ef69a2ff1e91f"}}