{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y2WWKYAFBJT4FHHIJICDHQKOS7","short_pith_number":"pith:Y2WWKYAF","canonical_record":{"source":{"id":"2506.10632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:17:40Z","cross_cats_sorted":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"title_canon_sha256":"fc9c35a6bcac278185f0f74ddb5114dceb904fa44d290bd7dfe75883af9e300a","abstract_canon_sha256":"4a40b513820ad7b2c53a43bf48237a7b6f9a218971452dabc34941a36309d001"},"schema_version":"1.0"},"canonical_sha256":"c6ad6560050a67c29ce84a0433c14e97d846518bf1f2ef77682cd6157d0696c6","source":{"kind":"arxiv","id":"2506.10632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10632","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10632v1","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10632","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"Y2WWKYAFBJT4","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"Y2WWKYAFBJT4FHHI","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"Y2WWKYAF","created_at":"2026-07-05T11:20:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y2WWKYAFBJT4FHHIJICDHQKOS7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.10632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:17:40Z","cross_cats_sorted":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"title_canon_sha256":"fc9c35a6bcac278185f0f74ddb5114dceb904fa44d290bd7dfe75883af9e300a","abstract_canon_sha256":"4a40b513820ad7b2c53a43bf48237a7b6f9a218971452dabc34941a36309d001"},"schema_version":"1.0"},"canonical_sha256":"c6ad6560050a67c29ce84a0433c14e97d846518bf1f2ef77682cd6157d0696c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:27.615746Z","signature_b64":"ln8b1nv/SJwSFi0ujVXYof23yHShaAj2xRNlS6DXFqHjuNSo86p0kgpcBvLOW+pXyFzJ5Ww0NPqoraW0ulnbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ad6560050a67c29ce84a0433c14e97d846518bf1f2ef77682cd6157d0696c6","last_reissued_at":"2026-07-05T11:20:27.615199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:27.615199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.10632","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":"2026-07-05T11:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyso+wak0wYNyZOsOjKkSLuYxkWAKdruu/g4o2euWGVnVm39QMf0piT500EDFUDK4rqvF86bZOu/HNwMN28MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:44:10.155882Z"},"content_sha256":"6fca8324db4b59e0d508dca94a866665a0ea4d906f7b60d243401e687d0c4568","schema_version":"1.0","event_id":"sha256:6fca8324db4b59e0d508dca94a866665a0ea4d906f7b60d243401e687d0c4568"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y2WWKYAFBJT4FHHIJICDHQKOS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hessian Geometry of Latent Space in Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Lobashev, Dmitry Guskov, Maria Larchenko, Mikhail Tamm","submitted_at":"2025-06-12T12:17:40Z","abstract_excerpt":"This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fisher information metric. The method approximates the posterior distribution of latent variables given generated samples and uses this to learn the log-partition function, which defines the Fisher metric for exponential families. Theoretical convergence guarantees are provided, and the method is validated on the Ising and TASEP models, outperforming existing baselines in reconstructing thermodynamic quantities. Applie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10632","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/2506.10632/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":"2026-07-05T11:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwNeO6w2ymCjMQqR4Xxk4qFrC/uVFeGFiXBn7+yWa8+gLget0lXfJOkjpcAZFXNvdyZ+/2758tcjPpK5LT7RAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:44:10.156270Z"},"content_sha256":"0b45aee0fe73857b7ae9135b9f75ff55715d2dd08bd33537f5f8dd5a4c7f191f","schema_version":"1.0","event_id":"sha256:0b45aee0fe73857b7ae9135b9f75ff55715d2dd08bd33537f5f8dd5a4c7f191f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/bundle.json","state_url":"https://pith.science/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/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":"2026-07-14T19:44:10Z","links":{"resolver":"https://pith.science/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7","bundle":"https://pith.science/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/bundle.json","state":"https://pith.science/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2WWKYAFBJT4FHHIJICDHQKOS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y2WWKYAFBJT4FHHIJICDHQKOS7","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":"4a40b513820ad7b2c53a43bf48237a7b6f9a218971452dabc34941a36309d001","cross_cats_sorted":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:17:40Z","title_canon_sha256":"fc9c35a6bcac278185f0f74ddb5114dceb904fa44d290bd7dfe75883af9e300a"},"schema_version":"1.0","source":{"id":"2506.10632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10632","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10632v1","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10632","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"Y2WWKYAFBJT4","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"Y2WWKYAFBJT4FHHI","created_at":"2026-07-05T11:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"Y2WWKYAF","created_at":"2026-07-05T11:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:0b45aee0fe73857b7ae9135b9f75ff55715d2dd08bd33537f5f8dd5a4c7f191f","target":"graph","created_at":"2026-07-05T11:20:27Z","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/2506.10632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fisher information metric. The method approximates the posterior distribution of latent variables given generated samples and uses this to learn the log-partition function, which defines the Fisher metric for exponential families. Theoretical convergence guarantees are provided, and the method is validated on the Ising and TASEP models, outperforming existing baselines in reconstructing thermodynamic quantities. Applie","authors_text":"Alexander Lobashev, Dmitry Guskov, Maria Larchenko, Mikhail Tamm","cross_cats":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:17:40Z","title":"Hessian Geometry of Latent Space in Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10632","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":"sha256:6fca8324db4b59e0d508dca94a866665a0ea4d906f7b60d243401e687d0c4568","target":"record","created_at":"2026-07-05T11:20:27Z","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":"4a40b513820ad7b2c53a43bf48237a7b6f9a218971452dabc34941a36309d001","cross_cats_sorted":["cond-mat.stat-mech","cs.CV","math.DG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T12:17:40Z","title_canon_sha256":"fc9c35a6bcac278185f0f74ddb5114dceb904fa44d290bd7dfe75883af9e300a"},"schema_version":"1.0","source":{"id":"2506.10632","kind":"arxiv","version":1}},"canonical_sha256":"c6ad6560050a67c29ce84a0433c14e97d846518bf1f2ef77682cd6157d0696c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6ad6560050a67c29ce84a0433c14e97d846518bf1f2ef77682cd6157d0696c6","first_computed_at":"2026-07-05T11:20:27.615199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:27.615199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ln8b1nv/SJwSFi0ujVXYof23yHShaAj2xRNlS6DXFqHjuNSo86p0kgpcBvLOW+pXyFzJ5Ww0NPqoraW0ulnbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:27.615746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fca8324db4b59e0d508dca94a866665a0ea4d906f7b60d243401e687d0c4568","sha256:0b45aee0fe73857b7ae9135b9f75ff55715d2dd08bd33537f5f8dd5a4c7f191f"],"state_sha256":"000bfc174027a10b330a32cefcb67e7226295190bfe325989bc31871643f95d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8dIeFY9gDjQBuvg8wLo9TuFtlzmxltYBQSK0ds3M64paLgFkMJpDnInVJcq5ppxvsKnYJK2udlTv4qQfY4cXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T19:44:10.158398Z","bundle_sha256":"c4532dbd3f308bb38c0f3e66da62cf51444c2c257e17f203c534c42febb603a6"}}