{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OCUGCY66SCYACBFLJ2DHU4QF5W","short_pith_number":"pith:OCUGCY66","canonical_record":{"source":{"id":"1902.01893","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T20:09:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"66be54f3d207623e89f850fb5576d301c9b2a5acdc47ef5512bfc3ebfa4c2f40","abstract_canon_sha256":"5518da18635529dfc7e414785a703cc1b1bf5d90b0927f0b9966b9b97166987c"},"schema_version":"1.0"},"canonical_sha256":"70a86163de90b00104ab4e867a7205ed8450e008efecd7a5bfb7b4be01fbc3d2","source":{"kind":"arxiv","id":"1902.01893","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01893","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01893v4","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01893","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"OCUGCY66SCYA","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCUGCY66SCYACBFL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCUGCY66","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OCUGCY66SCYACBFLJ2DHU4QF5W","target":"record","payload":{"canonical_record":{"source":{"id":"1902.01893","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T20:09:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"66be54f3d207623e89f850fb5576d301c9b2a5acdc47ef5512bfc3ebfa4c2f40","abstract_canon_sha256":"5518da18635529dfc7e414785a703cc1b1bf5d90b0927f0b9966b9b97166987c"},"schema_version":"1.0"},"canonical_sha256":"70a86163de90b00104ab4e867a7205ed8450e008efecd7a5bfb7b4be01fbc3d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:04.583778Z","signature_b64":"zrBKoGH/eSNm+PiiWTMsZC2mtbZX5bbYAbT5rwR9QztnAjRkl6V7G4mRw+X9OLFkWTtTXmg8ukzOSdaSIZplAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a86163de90b00104ab4e867a7205ed8450e008efecd7a5bfb7b4be01fbc3d2","last_reissued_at":"2026-05-17T23:48:04.583427Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:04.583427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.01893","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtYdGyCZpN6ohJvXiaksAMTrnAWEuLjFull4kSgLqB/HeQS1GPg457Kw496RKujuW491AAXiQWzkcdVnbMFkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:12:52.775750Z"},"content_sha256":"83b695397601d5d02160141d0f22834f18fe197976bf4400e9b41a64dfd1980e","schema_version":"1.0","event_id":"sha256:83b695397601d5d02160141d0f22834f18fe197976bf4400e9b41a64dfd1980e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OCUGCY66SCYACBFLJ2DHU4QF5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TzK: Flow-Based Conditional Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Fleet, Micha Livne","submitted_at":"2019-02-05T20:09:06Z","abstract_excerpt":"We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-conditionals or the joint distribution, and does not require a priori knowledge of the number of classes or the relationships between classes. This allows one to train generative models from multiple, heterogeneous datasets, while retaining strong prior models over subsets of the data (e.g., from a single dataset, class label, or attribute). In this paper, in addition to end-to-end learning, we show how one can learn a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01893","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAcLUPSOJEq5IBGxVSdjb9UdBH543jkRcLYmloLrdrOxqIKz0rEkOjGn3C8impS4Ha3a+VFOfPZ2BMP5YI18BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:12:52.776096Z"},"content_sha256":"025e07adac1538c96b0738549f5d25e153f53a8d7cac71306e85b3d507860217","schema_version":"1.0","event_id":"sha256:025e07adac1538c96b0738549f5d25e153f53a8d7cac71306e85b3d507860217"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/bundle.json","state_url":"https://pith.science/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/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":"2026-06-04T17:12:52Z","links":{"resolver":"https://pith.science/pith/OCUGCY66SCYACBFLJ2DHU4QF5W","bundle":"https://pith.science/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/bundle.json","state":"https://pith.science/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCUGCY66SCYACBFLJ2DHU4QF5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OCUGCY66SCYACBFLJ2DHU4QF5W","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":"5518da18635529dfc7e414785a703cc1b1bf5d90b0927f0b9966b9b97166987c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T20:09:06Z","title_canon_sha256":"66be54f3d207623e89f850fb5576d301c9b2a5acdc47ef5512bfc3ebfa4c2f40"},"schema_version":"1.0","source":{"id":"1902.01893","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01893","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01893v4","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01893","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"OCUGCY66SCYA","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCUGCY66SCYACBFL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCUGCY66","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:025e07adac1538c96b0738549f5d25e153f53a8d7cac71306e85b3d507860217","target":"graph","created_at":"2026-05-17T23:48:04Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-conditionals or the joint distribution, and does not require a priori knowledge of the number of classes or the relationships between classes. This allows one to train generative models from multiple, heterogeneous datasets, while retaining strong prior models over subsets of the data (e.g., from a single dataset, class label, or attribute). In this paper, in addition to end-to-end learning, we show how one can learn a si","authors_text":"David Fleet, Micha Livne","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T20:09:06Z","title":"TzK: Flow-Based Conditional Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01893","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:83b695397601d5d02160141d0f22834f18fe197976bf4400e9b41a64dfd1980e","target":"record","created_at":"2026-05-17T23:48:04Z","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":"5518da18635529dfc7e414785a703cc1b1bf5d90b0927f0b9966b9b97166987c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T20:09:06Z","title_canon_sha256":"66be54f3d207623e89f850fb5576d301c9b2a5acdc47ef5512bfc3ebfa4c2f40"},"schema_version":"1.0","source":{"id":"1902.01893","kind":"arxiv","version":4}},"canonical_sha256":"70a86163de90b00104ab4e867a7205ed8450e008efecd7a5bfb7b4be01fbc3d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70a86163de90b00104ab4e867a7205ed8450e008efecd7a5bfb7b4be01fbc3d2","first_computed_at":"2026-05-17T23:48:04.583427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:04.583427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zrBKoGH/eSNm+PiiWTMsZC2mtbZX5bbYAbT5rwR9QztnAjRkl6V7G4mRw+X9OLFkWTtTXmg8ukzOSdaSIZplAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:04.583778Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.01893","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83b695397601d5d02160141d0f22834f18fe197976bf4400e9b41a64dfd1980e","sha256:025e07adac1538c96b0738549f5d25e153f53a8d7cac71306e85b3d507860217"],"state_sha256":"44aaf1d1191b4bfd5fec75ac1d515c6326c6d16f300b276b2563ca689daaef5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYYzeC4MeQWKb/LrmKrxye5qulbwmWu6ae0mZ+9yN1uZHypCWlxaBQRmXz8Tupgwgm1gQOD6SJWhdwWen4PxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:12:52.778160Z","bundle_sha256":"daaed13ea2d76a2fb2fad4b3f7e58b0a85a5139ac06bdb8aa0e2f9b05196342f"}}