{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:K6CUN4JP2WRGVYDEINPU3MRVNT","short_pith_number":"pith:K6CUN4JP","schema_version":"1.0","canonical_sha256":"578546f12fd5a26ae064435f4db2356cc4ca13793fec9a3f82e370e4026d1141","source":{"kind":"arxiv","id":"2106.10410","version":2},"attestation_state":"computed","paper":{"title":"Deep Generative Learning via Schr\\\"{o}dinger Bridge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Can Yang, Gefei Wang, Qian Xu, Yang Wang, Yuling Jiao","submitted_at":"2021-06-19T03:35:42Z","abstract_excerpt":"We propose to learn a generative model via entropy interpolation with a Schr\\\"{o}dinger Bridge. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence. At the population level, this entropy interpolation is characterized via an SDE on $[0,1]$ with a time-varying drift term. At the sample level, we derive our Schr\\\"{o}dinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method. Under some mild sm"},"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":"2106.10410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-19T03:35:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"21ff53b1e81c864867f64f6e47e21361b7940736c2a62efc42e1fa3621c4e8cb","abstract_canon_sha256":"b0cfdae55cd1621ed21e71dc0c96c2fcedb73c2bc2b2a5d9c4329bb2f8f15826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:56.279894Z","signature_b64":"qsGCK7/o87oIVY58oY9IdTtgvKwi+LCRHrdGi0ANXwjRfp7fQNFahrDlNlBh9JHatksz/CrxnMi73RAzqJGgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"578546f12fd5a26ae064435f4db2356cc4ca13793fec9a3f82e370e4026d1141","last_reissued_at":"2026-07-05T03:01:56.279507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:56.279507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generative Learning via Schr\\\"{o}dinger Bridge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Can Yang, Gefei Wang, Qian Xu, Yang Wang, Yuling Jiao","submitted_at":"2021-06-19T03:35:42Z","abstract_excerpt":"We propose to learn a generative model via entropy interpolation with a Schr\\\"{o}dinger Bridge. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence. At the population level, this entropy interpolation is characterized via an SDE on $[0,1]$ with a time-varying drift term. At the sample level, we derive our Schr\\\"{o}dinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method. Under some mild sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10410","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/2106.10410/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":"2106.10410","created_at":"2026-07-05T03:01:56.279575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10410v2","created_at":"2026-07-05T03:01:56.279575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10410","created_at":"2026-07-05T03:01:56.279575+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6CUN4JP2WRG","created_at":"2026-07-05T03:01:56.279575+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6CUN4JP2WRGVYDE","created_at":"2026-07-05T03:01:56.279575+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6CUN4JP","created_at":"2026-07-05T03:01:56.279575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14190","citing_title":"Random-Bridges as Stochastic Transports for Generative Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT","json":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT.json","graph_json":"https://pith.science/api/pith-number/K6CUN4JP2WRGVYDEINPU3MRVNT/graph.json","events_json":"https://pith.science/api/pith-number/K6CUN4JP2WRGVYDEINPU3MRVNT/events.json","paper":"https://pith.science/paper/K6CUN4JP"},"agent_actions":{"view_html":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT","download_json":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT.json","view_paper":"https://pith.science/paper/K6CUN4JP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10410&json=true","fetch_graph":"https://pith.science/api/pith-number/K6CUN4JP2WRGVYDEINPU3MRVNT/graph.json","fetch_events":"https://pith.science/api/pith-number/K6CUN4JP2WRGVYDEINPU3MRVNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT/action/storage_attestation","attest_author":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT/action/author_attestation","sign_citation":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT/action/citation_signature","submit_replication":"https://pith.science/pith/K6CUN4JP2WRGVYDEINPU3MRVNT/action/replication_record"}},"created_at":"2026-07-05T03:01:56.279575+00:00","updated_at":"2026-07-05T03:01:56.279575+00:00"}