{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7INACJTNJKNBIXK77C4JMR63TY","short_pith_number":"pith:7INACJTN","canonical_record":{"source":{"id":"2409.20547","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-30T17:48:22Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"1719c21d7d1901dd9e59027f423f7cf46184cc92c0e3eccb0cd3515cd300d6d6","abstract_canon_sha256":"628c23a0f98a913a07b31c73ed21a5c8782480ce06ad61fc6ad0e8cbbc8cbd03"},"schema_version":"1.0"},"canonical_sha256":"fa1a01266d4a9a145d5ff8b89647db9e3d0d91e1f52ebc8f616bc2984eea1cef","source":{"kind":"arxiv","id":"2409.20547","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20547","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20547v4","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20547","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"7INACJTNJKNB","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"7INACJTNJKNBIXK7","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"7INACJTN","created_at":"2026-07-05T11:10:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7INACJTNJKNBIXK77C4JMR63TY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.20547","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-30T17:48:22Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"1719c21d7d1901dd9e59027f423f7cf46184cc92c0e3eccb0cd3515cd300d6d6","abstract_canon_sha256":"628c23a0f98a913a07b31c73ed21a5c8782480ce06ad61fc6ad0e8cbbc8cbd03"},"schema_version":"1.0"},"canonical_sha256":"fa1a01266d4a9a145d5ff8b89647db9e3d0d91e1f52ebc8f616bc2984eea1cef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:32.248544Z","signature_b64":"R7Gg+HRQaQQOxmgJXrtfjZYTsQiMOkIgsrpvfrsETNyVYAod5wL+916oLUMEz8lFv7IBPYGBdlban56iR/YWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa1a01266d4a9a145d5ff8b89647db9e3d0d91e1f52ebc8f616bc2984eea1cef","last_reissued_at":"2026-07-05T11:10:32.248042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:32.248042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.20547","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":"2026-07-05T11:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RvqNfGFpWkPw6z0aREB2CeRM7sPCqdqr+mA2F17Ykm31RbZ++NUhm1/dMY//wznxdxcM+7cF1uxWJNldbQWMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:17:50.700572Z"},"content_sha256":"900bc8550d60ec995f0c15b10ad23ad7f82057b3f3a0bf01d5ce6ad232d492ae","schema_version":"1.0","event_id":"sha256:900bc8550d60ec995f0c15b10ad23ad7f82057b3f3a0bf01d5ce6ad232d492ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7INACJTNJKNBIXK77C4JMR63TY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Dongze Wu, Yao Xie","submitted_at":"2024-09-30T17:48:22Z","abstract_excerpt":"Sampling from high-dimensional, multi-modal distributions remains a fundamental challenge across domains such as statistical Bayesian inference and physics-based machine learning. In this paper, we propose Annealing Flow (AF), a method built on Continuous Normalizing Flow (CNF) for sampling from high-dimensional and multi-modal distributions. AF is trained with a dynamic Optimal Transport (OT) objective incorporating Wasserstein regularization, and guided by annealing procedures, facilitating effective exploration of modes in high-dimensional spaces. Compared to recent NF methods, AF greatly i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20547","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.20547/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":"2026-07-05T11:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6dDvNmeh1r0iEn/UV5euyP/75R3zQOcqHLr/JRcsGDVb1ZmcNFPT/HaBEpRniILvZl+npwV/zu8SD/4zuRhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:17:50.701124Z"},"content_sha256":"3893ad033e13f3f7fa225e3ffe0ba6208a4e38ae5b01f936803a49ba71b554e1","schema_version":"1.0","event_id":"sha256:3893ad033e13f3f7fa225e3ffe0ba6208a4e38ae5b01f936803a49ba71b554e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7INACJTNJKNBIXK77C4JMR63TY/bundle.json","state_url":"https://pith.science/pith/7INACJTNJKNBIXK77C4JMR63TY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7INACJTNJKNBIXK77C4JMR63TY/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":"2026-08-10T09:17:50Z","links":{"resolver":"https://pith.science/pith/7INACJTNJKNBIXK77C4JMR63TY","bundle":"https://pith.science/pith/7INACJTNJKNBIXK77C4JMR63TY/bundle.json","state":"https://pith.science/pith/7INACJTNJKNBIXK77C4JMR63TY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7INACJTNJKNBIXK77C4JMR63TY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7INACJTNJKNBIXK77C4JMR63TY","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":"628c23a0f98a913a07b31c73ed21a5c8782480ce06ad61fc6ad0e8cbbc8cbd03","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-30T17:48:22Z","title_canon_sha256":"1719c21d7d1901dd9e59027f423f7cf46184cc92c0e3eccb0cd3515cd300d6d6"},"schema_version":"1.0","source":{"id":"2409.20547","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20547","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20547v4","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20547","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"7INACJTNJKNB","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"7INACJTNJKNBIXK7","created_at":"2026-07-05T11:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"7INACJTN","created_at":"2026-07-05T11:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:3893ad033e13f3f7fa225e3ffe0ba6208a4e38ae5b01f936803a49ba71b554e1","target":"graph","created_at":"2026-07-05T11:10:32Z","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/2409.20547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sampling from high-dimensional, multi-modal distributions remains a fundamental challenge across domains such as statistical Bayesian inference and physics-based machine learning. In this paper, we propose Annealing Flow (AF), a method built on Continuous Normalizing Flow (CNF) for sampling from high-dimensional and multi-modal distributions. AF is trained with a dynamic Optimal Transport (OT) objective incorporating Wasserstein regularization, and guided by annealing procedures, facilitating effective exploration of modes in high-dimensional spaces. Compared to recent NF methods, AF greatly i","authors_text":"Dongze Wu, Yao Xie","cross_cats":["cs.LG","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-30T17:48:22Z","title":"Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20547","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":"sha256:900bc8550d60ec995f0c15b10ad23ad7f82057b3f3a0bf01d5ce6ad232d492ae","target":"record","created_at":"2026-07-05T11:10:32Z","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":"628c23a0f98a913a07b31c73ed21a5c8782480ce06ad61fc6ad0e8cbbc8cbd03","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-30T17:48:22Z","title_canon_sha256":"1719c21d7d1901dd9e59027f423f7cf46184cc92c0e3eccb0cd3515cd300d6d6"},"schema_version":"1.0","source":{"id":"2409.20547","kind":"arxiv","version":4}},"canonical_sha256":"fa1a01266d4a9a145d5ff8b89647db9e3d0d91e1f52ebc8f616bc2984eea1cef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa1a01266d4a9a145d5ff8b89647db9e3d0d91e1f52ebc8f616bc2984eea1cef","first_computed_at":"2026-07-05T11:10:32.248042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:32.248042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R7Gg+HRQaQQOxmgJXrtfjZYTsQiMOkIgsrpvfrsETNyVYAod5wL+916oLUMEz8lFv7IBPYGBdlban56iR/YWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:32.248544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20547","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:900bc8550d60ec995f0c15b10ad23ad7f82057b3f3a0bf01d5ce6ad232d492ae","sha256:3893ad033e13f3f7fa225e3ffe0ba6208a4e38ae5b01f936803a49ba71b554e1"],"state_sha256":"99418cfebf15e19e55ebc3e2981ee638bba872ae101366141c9b19b89a90f25b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2fNwtp8GeVOwq4fpHJR+j1MJFrW71ofPhuxCn0Iqlqi5/+9+tlJ3AMg+ZlIc0u6uwcRgZP3i4IiBpGoSoMvnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:17:50.706493Z","bundle_sha256":"c5957f0121e7d596692a9462ddc677d0feaef022215f34d234a9d6e5232c66d4"}}