{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6V7XDF3EXIELKIL7UQWQ4RDYRD","short_pith_number":"pith:6V7XDF3E","canonical_record":{"source":{"id":"2505.03561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:13:21Z","cross_cats_sorted":["cs.AI","math.DG","math.DS"],"title_canon_sha256":"9d05a84c34ce115e1567bc35a9a5d975dc2fb9967d0f1c402fd0bdf0ca9becbc","abstract_canon_sha256":"d46db1ed6bddc860bb80a8a86262312531ffa89c7bccc97e6fc684f2715d6bc2"},"schema_version":"1.0"},"canonical_sha256":"f57f719764ba08b5217fa42d0e447888e18e797906a95a6eb7674040ab9a69f8","source":{"kind":"arxiv","id":"2505.03561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03561","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03561v1","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03561","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"6V7XDF3EXIEL","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_16","alias_value":"6V7XDF3EXIELKIL7","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_8","alias_value":"6V7XDF3E","created_at":"2026-07-05T10:59:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6V7XDF3EXIELKIL7UQWQ4RDYRD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:13:21Z","cross_cats_sorted":["cs.AI","math.DG","math.DS"],"title_canon_sha256":"9d05a84c34ce115e1567bc35a9a5d975dc2fb9967d0f1c402fd0bdf0ca9becbc","abstract_canon_sha256":"d46db1ed6bddc860bb80a8a86262312531ffa89c7bccc97e6fc684f2715d6bc2"},"schema_version":"1.0"},"canonical_sha256":"f57f719764ba08b5217fa42d0e447888e18e797906a95a6eb7674040ab9a69f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:18.297770Z","signature_b64":"Bsi0iO+tePU8muMjteOw111eFZO36uVUYdUo0vzKoE8W4GNASRXZ4qRQ0WCe5GzEZRCCtwPDb3TI7ondoe2JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f57f719764ba08b5217fa42d0e447888e18e797906a95a6eb7674040ab9a69f8","last_reissued_at":"2026-07-05T10:59:18.297193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:18.297193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03561","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":"2026-07-05T10:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mONdcDimwLpdJ9TfllaQ//oy9zjG+eF/jczoYf+wlQDhT/spzF93hznEbggOFY39vSLNpcSITIjh3fDhwZUFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:58:37.363741Z"},"content_sha256":"4bc0faf7bc6244774996977e3021995d68debc6af4366c64ce2921bb52fc110d","schema_version":"1.0","event_id":"sha256:4bc0faf7bc6244774996977e3021995d68debc6af4366c64ce2921bb52fc110d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6V7XDF3EXIELKIL7UQWQ4RDYRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ergodic Generative Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DG","math.DS"],"primary_cat":"cs.LG","authors_text":"Adam Sigal, Amir Rasouli, Leo Maxime Brunswic, Mateo Clemente, Rui Heng Yang, Yinchuan Li","submitted_at":"2025-05-06T14:13:21Z","abstract_excerpt":"Generative Flow Networks (GFNs) were initially introduced on directed acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical framework for generative methods allowing more flexibility and enhancing application range. However, many challenges remain in training GFNs in continuous settings and for imitation learning (IL), including intractability of flow-matching loss, limited tests of non-acyclic training, and the need for a separate reward model in imitation learning. The present work proposes a family of generative flows called Ergodic G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03561","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/2505.03561/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":"2026-07-05T10:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8QRCyoNj+o1zrdNwyZUntfjO/24M90XH86hLxmFpVlqe97lS3/+8W3yVWTQN25qPKA+nLoEB1M0VG28BKIsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:58:37.364655Z"},"content_sha256":"43552a1dc09eca93a355c3e9a4be23936ba130a123324ebe69ee954b6fd83177","schema_version":"1.0","event_id":"sha256:43552a1dc09eca93a355c3e9a4be23936ba130a123324ebe69ee954b6fd83177"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/bundle.json","state_url":"https://pith.science/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/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":"2026-08-09T00:58:37Z","links":{"resolver":"https://pith.science/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD","bundle":"https://pith.science/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/bundle.json","state":"https://pith.science/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6V7XDF3EXIELKIL7UQWQ4RDYRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6V7XDF3EXIELKIL7UQWQ4RDYRD","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":"d46db1ed6bddc860bb80a8a86262312531ffa89c7bccc97e6fc684f2715d6bc2","cross_cats_sorted":["cs.AI","math.DG","math.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:13:21Z","title_canon_sha256":"9d05a84c34ce115e1567bc35a9a5d975dc2fb9967d0f1c402fd0bdf0ca9becbc"},"schema_version":"1.0","source":{"id":"2505.03561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03561","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03561v1","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03561","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"6V7XDF3EXIEL","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_16","alias_value":"6V7XDF3EXIELKIL7","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_8","alias_value":"6V7XDF3E","created_at":"2026-07-05T10:59:18Z"}],"graph_snapshots":[{"event_id":"sha256:43552a1dc09eca93a355c3e9a4be23936ba130a123324ebe69ee954b6fd83177","target":"graph","created_at":"2026-07-05T10:59:18Z","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/2505.03561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Flow Networks (GFNs) were initially introduced on directed acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical framework for generative methods allowing more flexibility and enhancing application range. However, many challenges remain in training GFNs in continuous settings and for imitation learning (IL), including intractability of flow-matching loss, limited tests of non-acyclic training, and the need for a separate reward model in imitation learning. The present work proposes a family of generative flows called Ergodic G","authors_text":"Adam Sigal, Amir Rasouli, Leo Maxime Brunswic, Mateo Clemente, Rui Heng Yang, Yinchuan Li","cross_cats":["cs.AI","math.DG","math.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:13:21Z","title":"Ergodic Generative Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03561","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":"sha256:4bc0faf7bc6244774996977e3021995d68debc6af4366c64ce2921bb52fc110d","target":"record","created_at":"2026-07-05T10:59:18Z","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":"d46db1ed6bddc860bb80a8a86262312531ffa89c7bccc97e6fc684f2715d6bc2","cross_cats_sorted":["cs.AI","math.DG","math.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:13:21Z","title_canon_sha256":"9d05a84c34ce115e1567bc35a9a5d975dc2fb9967d0f1c402fd0bdf0ca9becbc"},"schema_version":"1.0","source":{"id":"2505.03561","kind":"arxiv","version":1}},"canonical_sha256":"f57f719764ba08b5217fa42d0e447888e18e797906a95a6eb7674040ab9a69f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f57f719764ba08b5217fa42d0e447888e18e797906a95a6eb7674040ab9a69f8","first_computed_at":"2026-07-05T10:59:18.297193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:18.297193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bsi0iO+tePU8muMjteOw111eFZO36uVUYdUo0vzKoE8W4GNASRXZ4qRQ0WCe5GzEZRCCtwPDb3TI7ondoe2JDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:18.297770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bc0faf7bc6244774996977e3021995d68debc6af4366c64ce2921bb52fc110d","sha256:43552a1dc09eca93a355c3e9a4be23936ba130a123324ebe69ee954b6fd83177"],"state_sha256":"8935c369a7128f3d84913a15d3e3e41d75d69682f6f2239ac76b28fdadfb297d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4wMAIMfNJy1yNr2b0xPrHApZ1YmFs5E6V5WWvh8/ZcGGzRQ4bezMwSBk8tgQZm00dKci+2L/psSpvX8RfjVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:58:37.369835Z","bundle_sha256":"67e03780a2d7d8f33395b7cb9cc9c5977e3d1ba36911bd565a1648d20e881334"}}