{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UPRRH6Q6O63C3WFU7QTJUL5QDM","short_pith_number":"pith:UPRRH6Q6","canonical_record":{"source":{"id":"2310.16624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T13:23:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8335176840e808238b173da1510da061371f254a9f2cfdc5916329e9368dba86","abstract_canon_sha256":"b7b1305f78f2172ce786b4a4070b109ff3acc8bd0d1593190f70f2457815ee37"},"schema_version":"1.0"},"canonical_sha256":"a3e313fa1e77b62dd8b4fc269a2fb01b36e7069828b09f7ff2e241b0da57b3e9","source":{"kind":"arxiv","id":"2310.16624","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16624","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16624v2","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16624","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"UPRRH6Q6O63C","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"UPRRH6Q6O63C3WFU","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"UPRRH6Q6","created_at":"2026-07-05T08:11:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UPRRH6Q6O63C3WFU7QTJUL5QDM","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T13:23:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8335176840e808238b173da1510da061371f254a9f2cfdc5916329e9368dba86","abstract_canon_sha256":"b7b1305f78f2172ce786b4a4070b109ff3acc8bd0d1593190f70f2457815ee37"},"schema_version":"1.0"},"canonical_sha256":"a3e313fa1e77b62dd8b4fc269a2fb01b36e7069828b09f7ff2e241b0da57b3e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:40.204533Z","signature_b64":"S7VDud/qBGyhagvBwBpVBeECz/xNP6gND7t9EChkGGHvWyzOWGf6UEGDdoQEXZx859TixaqM5fqcC0tZqlseDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3e313fa1e77b62dd8b4fc269a2fb01b36e7069828b09f7ff2e241b0da57b3e9","last_reissued_at":"2026-07-05T08:11:40.204095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:40.204095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16624","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":"2026-07-05T08:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EuCnuNeBw2N/Z+A2fffOQyuO4DkEMa4ZDdzJU601RIVbowuzhX9P9QEE/IgMhov5laRGKfNKSCspNjftoIqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:11:05.505036Z"},"content_sha256":"043c5167ef8c28e970940c80f3a8394e4d902f25bf230072b73fc441fdb875d0","schema_version":"1.0","event_id":"sha256:043c5167ef8c28e970940c80f3a8394e4d902f25bf230072b73fc441fdb875d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UPRRH6Q6O63C3WFU7QTJUL5QDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Free-form Flows: Make Any Architecture a Normalizing Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Armand Rousselot, Felix Draxler, Lea Zimmermann, Peter Sorrenson, Ullrich K\\\"othe","submitted_at":"2023-10-25T13:23:08Z","abstract_excerpt":"Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure that uses an efficient estimator for the gradient of the change of variables formula. This enables any dimension-preserving neural network to serve as a generative model through maximum likelihood training. Our approach allows placing the emphasis on tailoring inductive biases precisely to the task at hand. Specifically, we achieve excellent results in mole"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16624","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/2310.16624/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtrsGyfd5TYW5ZoFP39AvtGZA2R9ew5MScu/CjkWnaEynynneLH3WcCcAfW02M9ju8iXUPNrs4Gy0gq+yi6VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:11:05.505640Z"},"content_sha256":"4f2260be9bb542c40e1bfae6d181cb19db7cceeb9f2ff5f8fa946fd96470b7e1","schema_version":"1.0","event_id":"sha256:4f2260be9bb542c40e1bfae6d181cb19db7cceeb9f2ff5f8fa946fd96470b7e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/bundle.json","state_url":"https://pith.science/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/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":"2026-08-12T21:11:05Z","links":{"resolver":"https://pith.science/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM","bundle":"https://pith.science/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/bundle.json","state":"https://pith.science/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPRRH6Q6O63C3WFU7QTJUL5QDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UPRRH6Q6O63C3WFU7QTJUL5QDM","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":"b7b1305f78f2172ce786b4a4070b109ff3acc8bd0d1593190f70f2457815ee37","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T13:23:08Z","title_canon_sha256":"8335176840e808238b173da1510da061371f254a9f2cfdc5916329e9368dba86"},"schema_version":"1.0","source":{"id":"2310.16624","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16624","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16624v2","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16624","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"UPRRH6Q6O63C","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"UPRRH6Q6O63C3WFU","created_at":"2026-07-05T08:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"UPRRH6Q6","created_at":"2026-07-05T08:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:4f2260be9bb542c40e1bfae6d181cb19db7cceeb9f2ff5f8fa946fd96470b7e1","target":"graph","created_at":"2026-07-05T08:11:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.16624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure that uses an efficient estimator for the gradient of the change of variables formula. This enables any dimension-preserving neural network to serve as a generative model through maximum likelihood training. Our approach allows placing the emphasis on tailoring inductive biases precisely to the task at hand. Specifically, we achieve excellent results in mole","authors_text":"Armand Rousselot, Felix Draxler, Lea Zimmermann, Peter Sorrenson, Ullrich K\\\"othe","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T13:23:08Z","title":"Free-form Flows: Make Any Architecture a Normalizing Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16624","kind":"arxiv","version":2},"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":"sha256:043c5167ef8c28e970940c80f3a8394e4d902f25bf230072b73fc441fdb875d0","target":"record","created_at":"2026-07-05T08:11:40Z","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":"b7b1305f78f2172ce786b4a4070b109ff3acc8bd0d1593190f70f2457815ee37","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T13:23:08Z","title_canon_sha256":"8335176840e808238b173da1510da061371f254a9f2cfdc5916329e9368dba86"},"schema_version":"1.0","source":{"id":"2310.16624","kind":"arxiv","version":2}},"canonical_sha256":"a3e313fa1e77b62dd8b4fc269a2fb01b36e7069828b09f7ff2e241b0da57b3e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3e313fa1e77b62dd8b4fc269a2fb01b36e7069828b09f7ff2e241b0da57b3e9","first_computed_at":"2026-07-05T08:11:40.204095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:40.204095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S7VDud/qBGyhagvBwBpVBeECz/xNP6gND7t9EChkGGHvWyzOWGf6UEGDdoQEXZx859TixaqM5fqcC0tZqlseDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:40.204533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16624","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:043c5167ef8c28e970940c80f3a8394e4d902f25bf230072b73fc441fdb875d0","sha256:4f2260be9bb542c40e1bfae6d181cb19db7cceeb9f2ff5f8fa946fd96470b7e1"],"state_sha256":"c493440e19cea4d2a34d547b6dc4c956273c92eb97241fcd06bd4b26c7ef8471"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tGEFx2TSMNPNwdMp9ZnkrxzR+aKFf47TPec0gmbGKuBavnOMRDT9VCO6B+uT73iugd34eub3IcpMnShuANwkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:11:05.514002Z","bundle_sha256":"60e3ebb334e480b6e5cbf192816e113a5a843e6654e0f48bbc8dc12ebce6f972"}}