{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FI24JQFBGPUOQHYAOYKFL7BF2H","short_pith_number":"pith:FI24JQFB","schema_version":"1.0","canonical_sha256":"2a35c4c0a133e8e81f00761455fc25d1f786c85585800030c78265e056f76468","source":{"kind":"arxiv","id":"2310.03725","version":3},"attestation_state":"computed","paper":{"title":"Stochastic interpolants with data-dependent couplings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Mark Goldstein, Michael S. Albergo, Nicholas M. Boffi, Rajesh Ranganath","submitted_at":"2023-10-05T17:46:31Z","abstract_excerpt":"Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, one of these is the target density, only accessible through samples, while the other is taken as a simple base density that is data-agnostic. In this work, using the framework of stochastic interpolants, we formalize how to \\textit{couple} the base and the target densities, whereby samples from the base are computed conditionally given samples from the target in a way that is different from (but does preclude) incorpo"},"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":"2310.03725","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T17:46:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4e2f55300f12c323041b7beac16cc296422c63a852b3521bd565a63fcc76f624","abstract_canon_sha256":"32cb409a4300c60c862fc3e74bc6ded63a145f07557e8464176eef39a67b059c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:29.388769Z","signature_b64":"tzZw4nZ8/+nRgN+wgOt3jGcN4JQe+CRNa8NbWC1EhacSBEad4Zvw/3dtTWqn/6RT0QHY50bp8ZbHfyClMi6AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a35c4c0a133e8e81f00761455fc25d1f786c85585800030c78265e056f76468","last_reissued_at":"2026-07-05T09:10:29.388301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:29.388301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic interpolants with data-dependent couplings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Mark Goldstein, Michael S. Albergo, Nicholas M. Boffi, Rajesh Ranganath","submitted_at":"2023-10-05T17:46:31Z","abstract_excerpt":"Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, one of these is the target density, only accessible through samples, while the other is taken as a simple base density that is data-agnostic. In this work, using the framework of stochastic interpolants, we formalize how to \\textit{couple} the base and the target densities, whereby samples from the base are computed conditionally given samples from the target in a way that is different from (but does preclude) incorpo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03725","kind":"arxiv","version":3},"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/2310.03725/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":"2310.03725","created_at":"2026-07-05T09:10:29.388371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03725v3","created_at":"2026-07-05T09:10:29.388371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03725","created_at":"2026-07-05T09:10:29.388371+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI24JQFBGPUO","created_at":"2026-07-05T09:10:29.388371+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI24JQFBGPUOQHYA","created_at":"2026-07-05T09:10:29.388371+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI24JQFB","created_at":"2026-07-05T09:10:29.388371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23949","citing_title":"Variational inference and density estimation with non-negative tensor of hierarchical tucker format","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22630","citing_title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19651","citing_title":"BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00196","citing_title":"TRIE: An Evaluation Framework for Stochastic PDE Surrogates","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28507","citing_title":"Universal Time Series Generation with Neural Controlled Differential Equations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20098","citing_title":"Incomplete Data, Complete Dynamics: A Diffusion Approach","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10857","citing_title":"Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H","json":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H.json","graph_json":"https://pith.science/api/pith-number/FI24JQFBGPUOQHYAOYKFL7BF2H/graph.json","events_json":"https://pith.science/api/pith-number/FI24JQFBGPUOQHYAOYKFL7BF2H/events.json","paper":"https://pith.science/paper/FI24JQFB"},"agent_actions":{"view_html":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H","download_json":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H.json","view_paper":"https://pith.science/paper/FI24JQFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03725&json=true","fetch_graph":"https://pith.science/api/pith-number/FI24JQFBGPUOQHYAOYKFL7BF2H/graph.json","fetch_events":"https://pith.science/api/pith-number/FI24JQFBGPUOQHYAOYKFL7BF2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H/action/storage_attestation","attest_author":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H/action/author_attestation","sign_citation":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H/action/citation_signature","submit_replication":"https://pith.science/pith/FI24JQFBGPUOQHYAOYKFL7BF2H/action/replication_record"}},"created_at":"2026-07-05T09:10:29.388371+00:00","updated_at":"2026-07-05T09:10:29.388371+00:00"}