{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AAJBQHVM7ATTPWKHZPVWELR7EK","short_pith_number":"pith:AAJBQHVM","canonical_record":{"source":{"id":"2505.23527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T15:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"bfc98c39c2aa8c27cb191d830ce180bb1b60c04a914004e26b630c6ec04d9747","abstract_canon_sha256":"5df55698a4f93e699821775b27aef8823f05c28a8a91fe0cca5a340a207a7d96"},"schema_version":"1.0"},"canonical_sha256":"0012181eacf82737d947cbeb622e3f2283b28ce929bec9515ff21795c3724850","source":{"kind":"arxiv","id":"2505.23527","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23527","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23527v4","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23527","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"AAJBQHVM7ATT","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"AAJBQHVM7ATTPWKH","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"AAJBQHVM","created_at":"2026-06-26T01:15:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AAJBQHVM7ATTPWKHZPVWELR7EK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T15:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"bfc98c39c2aa8c27cb191d830ce180bb1b60c04a914004e26b630c6ec04d9747","abstract_canon_sha256":"5df55698a4f93e699821775b27aef8823f05c28a8a91fe0cca5a340a207a7d96"},"schema_version":"1.0"},"canonical_sha256":"0012181eacf82737d947cbeb622e3f2283b28ce929bec9515ff21795c3724850","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:44.316438Z","signature_b64":"9DrfpMBm3Nk2QNQFIUttOZa8PoseEQWEma91rpG9cSZcsnFIu7pDI3Hf4faD9fu86us7SDBCG2UDnsy6w+NuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0012181eacf82737d947cbeb622e3f2283b28ce929bec9515ff21795c3724850","last_reissued_at":"2026-06-26T01:15:44.315943Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:44.315943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23527","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":"2026-06-26T01:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"euU95M0m4rKDacIGpwnsVkYK4xM4upjpBVWl1B1sLCpnx7ihKtq2uftLwPrhbn+0cVmgcOXiDme7S+r47btYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T10:33:08.336391Z"},"content_sha256":"53dc125008ecfe2d18e84b0415212d29f5664ad13473c1d85cdea1469aa91184","schema_version":"1.0","event_id":"sha256:53dc125008ecfe2d18e84b0415212d29f5664ad13473c1d85cdea1469aa91184"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AAJBQHVM7ATTPWKHZPVWELR7EK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Normalizing Flows are Capable Models for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Raj Ghugare","submitted_at":"2025-05-29T15:06:22Z","abstract_excerpt":"Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price of accommodating these models into their algorithms -- diffusion models are expressive, but are computationally intensive due to their reliance on solving differential equations, while autoregressive transformer models are scalable but typically require learning discrete representations. Normalizing flows (NFs), by contrast, seem to provide an appealing alter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23527","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/2505.23527/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":"2026-06-26T01:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/i+HziJyixEhBjPmiDkKl+Lgd1t8/8WkabRQiu4ZonbhGD1oezQ0vNwroFVKkw9tgfMMORRPKWNpxANdWfheAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T10:33:08.336768Z"},"content_sha256":"8a28e55f68065d18ad9350f9dec436d0e860a1e3d37023489493b41de6ba1e16","schema_version":"1.0","event_id":"sha256:8a28e55f68065d18ad9350f9dec436d0e860a1e3d37023489493b41de6ba1e16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/bundle.json","state_url":"https://pith.science/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/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":"2026-07-02T10:33:08Z","links":{"resolver":"https://pith.science/pith/AAJBQHVM7ATTPWKHZPVWELR7EK","bundle":"https://pith.science/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/bundle.json","state":"https://pith.science/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAJBQHVM7ATTPWKHZPVWELR7EK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AAJBQHVM7ATTPWKHZPVWELR7EK","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":"5df55698a4f93e699821775b27aef8823f05c28a8a91fe0cca5a340a207a7d96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T15:06:22Z","title_canon_sha256":"bfc98c39c2aa8c27cb191d830ce180bb1b60c04a914004e26b630c6ec04d9747"},"schema_version":"1.0","source":{"id":"2505.23527","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23527","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23527v4","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23527","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"AAJBQHVM7ATT","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"AAJBQHVM7ATTPWKH","created_at":"2026-06-26T01:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"AAJBQHVM","created_at":"2026-06-26T01:15:44Z"}],"graph_snapshots":[{"event_id":"sha256:8a28e55f68065d18ad9350f9dec436d0e860a1e3d37023489493b41de6ba1e16","target":"graph","created_at":"2026-06-26T01:15:44Z","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/2505.23527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price of accommodating these models into their algorithms -- diffusion models are expressive, but are computationally intensive due to their reliance on solving differential equations, while autoregressive transformer models are scalable but typically require learning discrete representations. Normalizing flows (NFs), by contrast, seem to provide an appealing alter","authors_text":"Benjamin Eysenbach, Raj Ghugare","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T15:06:22Z","title":"Normalizing Flows are Capable Models for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23527","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":"sha256:53dc125008ecfe2d18e84b0415212d29f5664ad13473c1d85cdea1469aa91184","target":"record","created_at":"2026-06-26T01:15:44Z","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":"5df55698a4f93e699821775b27aef8823f05c28a8a91fe0cca5a340a207a7d96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T15:06:22Z","title_canon_sha256":"bfc98c39c2aa8c27cb191d830ce180bb1b60c04a914004e26b630c6ec04d9747"},"schema_version":"1.0","source":{"id":"2505.23527","kind":"arxiv","version":4}},"canonical_sha256":"0012181eacf82737d947cbeb622e3f2283b28ce929bec9515ff21795c3724850","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0012181eacf82737d947cbeb622e3f2283b28ce929bec9515ff21795c3724850","first_computed_at":"2026-06-26T01:15:44.315943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:44.315943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9DrfpMBm3Nk2QNQFIUttOZa8PoseEQWEma91rpG9cSZcsnFIu7pDI3Hf4faD9fu86us7SDBCG2UDnsy6w+NuDg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:44.316438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23527","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53dc125008ecfe2d18e84b0415212d29f5664ad13473c1d85cdea1469aa91184","sha256:8a28e55f68065d18ad9350f9dec436d0e860a1e3d37023489493b41de6ba1e16"],"state_sha256":"eeaf970b3be789b3f02f8e9b4df16eea1d5ff8ec2104477d3746aabd79eed4d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hf2XI88tb5gJJ7+Ryg2olfdZus0cdkxlTGOQL1ITWzBC5FhLXDNB5RKfR7sFmYoRPK/HoHLLmKm8MFP3GHzBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T10:33:08.338793Z","bundle_sha256":"9aecbc2d42ace93a1ada4a6d8bb1c085b5ecb9ddc04badd0f9b0d0ec402059fc"}}