{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6HCM4Y5RGB2CGI5L2JFXZ5OWRW","short_pith_number":"pith:6HCM4Y5R","canonical_record":{"source":{"id":"2607.00947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:46:22Z","cross_cats_sorted":[],"title_canon_sha256":"c6e141d9ac9fd9082d74192c353cd84ed8944d1337744eafc8247ae56b767b27","abstract_canon_sha256":"c487f8e007356552cdf933b7c881d0658b6f3847c6714994fc17cc0c00d45c7e"},"schema_version":"1.0"},"canonical_sha256":"f1c4ce63b130742323abd24b7cf5d68d9a9289fd11f6ca100448ee733bb2e2f2","source":{"kind":"arxiv","id":"2607.00947","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00947","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00947v1","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00947","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"6HCM4Y5RGB2C","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"6HCM4Y5RGB2CGI5L","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"6HCM4Y5R","created_at":"2026-07-02T01:18:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6HCM4Y5RGB2CGI5L2JFXZ5OWRW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:46:22Z","cross_cats_sorted":[],"title_canon_sha256":"c6e141d9ac9fd9082d74192c353cd84ed8944d1337744eafc8247ae56b767b27","abstract_canon_sha256":"c487f8e007356552cdf933b7c881d0658b6f3847c6714994fc17cc0c00d45c7e"},"schema_version":"1.0"},"canonical_sha256":"f1c4ce63b130742323abd24b7cf5d68d9a9289fd11f6ca100448ee733bb2e2f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:24.225753Z","signature_b64":"0CcORcm7LS719aFqaSv5GlDClBoL9mKsWQjFelCKGMLSNGtYfGr3VhqsDxeI8Nk8ce/MLDkbv3d6X5x5NJN5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1c4ce63b130742323abd24b7cf5d68d9a9289fd11f6ca100448ee733bb2e2f2","last_reissued_at":"2026-07-02T01:18:24.225369Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:24.225369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00947","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:18:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wtAWxdhlg4JQi3ANBkbpmCoqmn8rje1HtCHi7rCflZQftVil0aiJSNQPj74SE4u4jOYGeVc/cm8g9njlPeMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:12:16.881954Z"},"content_sha256":"8853fe4dc52aae487f99f67e7de946d4ba268811492fca96fb64af51371d8069","schema_version":"1.0","event_id":"sha256:8853fe4dc52aae487f99f67e7de946d4ba268811492fca96fb64af51371d8069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6HCM4Y5RGB2CGI5L2JFXZ5OWRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffeomorphic Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Leaver-Fay, Joseph Kleinhenz, Ludwig Winkler, Pan Kessel","submitted_at":"2026-07-01T13:46:22Z","abstract_excerpt":"Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space. Optimizing differentiable objectives on this manifold is challenging: the ambient loss landscape is high-dimensional, rugged, and non-convex. Direct gradient descent, blind to the manifold's geometry, quickly drifts off it. Diffeomorphic optimization starts from the observation that diffusion and flow models provide a map from the data manifold to a much simpler base space in which we perform gradient descent. Using differential geometry, we show this is equivalent to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00947","kind":"arxiv","version":1},"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/2607.00947/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":"2026-07-02T01:18:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+wopsnrmwF/QYqtidfnwz+q8rukmKY6kIG2sVZ+7JM9erWzk/X3+0yQGYHFTSyy2H5nDSvF5p3qemJQm7v0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:12:16.882337Z"},"content_sha256":"d37a2e7fd9ed9faf70490b0eb42cb917cda01363886118a357bea2e8304a6dcd","schema_version":"1.0","event_id":"sha256:d37a2e7fd9ed9faf70490b0eb42cb917cda01363886118a357bea2e8304a6dcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/bundle.json","state_url":"https://pith.science/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/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":"2026-07-02T19:12:16Z","links":{"resolver":"https://pith.science/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW","bundle":"https://pith.science/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/bundle.json","state":"https://pith.science/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HCM4Y5RGB2CGI5L2JFXZ5OWRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HCM4Y5RGB2CGI5L2JFXZ5OWRW","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":"c487f8e007356552cdf933b7c881d0658b6f3847c6714994fc17cc0c00d45c7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:46:22Z","title_canon_sha256":"c6e141d9ac9fd9082d74192c353cd84ed8944d1337744eafc8247ae56b767b27"},"schema_version":"1.0","source":{"id":"2607.00947","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00947","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00947v1","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00947","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"6HCM4Y5RGB2C","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"6HCM4Y5RGB2CGI5L","created_at":"2026-07-02T01:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"6HCM4Y5R","created_at":"2026-07-02T01:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:d37a2e7fd9ed9faf70490b0eb42cb917cda01363886118a357bea2e8304a6dcd","target":"graph","created_at":"2026-07-02T01:18:24Z","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/2607.00947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space. Optimizing differentiable objectives on this manifold is challenging: the ambient loss landscape is high-dimensional, rugged, and non-convex. Direct gradient descent, blind to the manifold's geometry, quickly drifts off it. Diffeomorphic optimization starts from the observation that diffusion and flow models provide a map from the data manifold to a much simpler base space in which we perform gradient descent. Using differential geometry, we show this is equivalent to","authors_text":"Andrew Leaver-Fay, Joseph Kleinhenz, Ludwig Winkler, Pan Kessel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:46:22Z","title":"Diffeomorphic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00947","kind":"arxiv","version":1},"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":"sha256:8853fe4dc52aae487f99f67e7de946d4ba268811492fca96fb64af51371d8069","target":"record","created_at":"2026-07-02T01:18:24Z","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":"c487f8e007356552cdf933b7c881d0658b6f3847c6714994fc17cc0c00d45c7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:46:22Z","title_canon_sha256":"c6e141d9ac9fd9082d74192c353cd84ed8944d1337744eafc8247ae56b767b27"},"schema_version":"1.0","source":{"id":"2607.00947","kind":"arxiv","version":1}},"canonical_sha256":"f1c4ce63b130742323abd24b7cf5d68d9a9289fd11f6ca100448ee733bb2e2f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1c4ce63b130742323abd24b7cf5d68d9a9289fd11f6ca100448ee733bb2e2f2","first_computed_at":"2026-07-02T01:18:24.225369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:24.225369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0CcORcm7LS719aFqaSv5GlDClBoL9mKsWQjFelCKGMLSNGtYfGr3VhqsDxeI8Nk8ce/MLDkbv3d6X5x5NJN5Dw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:24.225753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00947","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8853fe4dc52aae487f99f67e7de946d4ba268811492fca96fb64af51371d8069","sha256:d37a2e7fd9ed9faf70490b0eb42cb917cda01363886118a357bea2e8304a6dcd"],"state_sha256":"3ca76fe2710a4163c31a1131c2fbf5d68dab923839ca30ecdb720b676393fed8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0WY4bGV9tX3wn6PcpshYGj92a9eiIkgj7hTb0g4au6oyvsNsRCIuJUKjK2zQUXRFGR6KdpcZA6b+VbBrzmODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:12:16.884307Z","bundle_sha256":"278381ea5a8bed7682a027fb46742e607a3631248a9ab0149cd0f4ddeccfe2c4"}}