{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","short_pith_number":"pith:TCMMLHA7","canonical_record":{"source":{"id":"2502.02316","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","cross_cats_sorted":[],"title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6","abstract_canon_sha256":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa"},"schema_version":"1.0"},"canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","source":{"kind":"arxiv","id":"2502.02316","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02316v2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCMMLHA7FOZ2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCMMLHA7FOZ2QXXR","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCMMLHA7","created_at":"2026-07-05T11:19:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02316","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","cross_cats_sorted":[],"title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6","abstract_canon_sha256":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa"},"schema_version":"1.0"},"canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:03.270282Z","signature_b64":"vjsvglqua2XRYPO/2af7b579iqcKUWK087QfegQs0fl1kM8u9IbKMi6hcpn8vTxKK3tPjzLPxyJ7g8JVGNCICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","last_reissued_at":"2026-07-05T11:19:03.269813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:03.269813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02316","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oDFDfn2AYXROOqA0WrWODgITk9QEqvkGwTb5w8Dn6YWRXRgaBpZjEDsSrTPVnXEFVPdYzyttP29pVyG9UCOXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:29:16.402721Z"},"content_sha256":"1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285","schema_version":"1.0","event_id":"sha256:1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Palenicek, Denis Blessing, Ge Li, Georgia Chalvatzaki, Gerhard Neumann, Jan Peters, Onur Celik, Zechu Li","submitted_at":"2025-02-04T13:37:14Z","abstract_excerpt":"Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their representational capacity. Diffusion-based policies offer a more expressive alternative, yet integrating them into MaxEnt-RL poses challenges-primarily due to the intractability of computing their marginal entropy. To overcome this, we propose Diffusion-Based Maximum Entropy RL (DIME). \\emph{DIME} leverages recent advances in approximate inference with diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02316","kind":"arxiv","version":2},"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/2502.02316/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":"2026-07-05T11:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvzzsfKQ/yshFTy1TIKpnk0KsgWDqzTsoS+mNNGV0xPFyLMhNbgMGVPOwLkG+m5gF5JQSvadMakf6RNQbpBZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:29:16.403503Z"},"content_sha256":"e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f","schema_version":"1.0","event_id":"sha256:e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/bundle.json","state_url":"https://pith.science/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/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":"2026-08-10T00:29:16Z","links":{"resolver":"https://pith.science/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","bundle":"https://pith.science/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/bundle.json","state":"https://pith.science/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCMMLHA7FOZ2QXXRZ4TFZ77V5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","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":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6"},"schema_version":"1.0","source":{"id":"2502.02316","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02316v2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCMMLHA7FOZ2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCMMLHA7FOZ2QXXR","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCMMLHA7","created_at":"2026-07-05T11:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f","target":"graph","created_at":"2026-07-05T11:19:03Z","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/2502.02316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their representational capacity. Diffusion-based policies offer a more expressive alternative, yet integrating them into MaxEnt-RL poses challenges-primarily due to the intractability of computing their marginal entropy. To overcome this, we propose Diffusion-Based Maximum Entropy RL (DIME). \\emph{DIME} leverages recent advances in approximate inference with diff","authors_text":"Daniel Palenicek, Denis Blessing, Ge Li, Georgia Chalvatzaki, Gerhard Neumann, Jan Peters, Onur Celik, Zechu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02316","kind":"arxiv","version":2},"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":"sha256:1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285","target":"record","created_at":"2026-07-05T11:19:03Z","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":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6"},"schema_version":"1.0","source":{"id":"2502.02316","kind":"arxiv","version":2}},"canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","first_computed_at":"2026-07-05T11:19:03.269813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:03.269813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vjsvglqua2XRYPO/2af7b579iqcKUWK087QfegQs0fl1kM8u9IbKMi6hcpn8vTxKK3tPjzLPxyJ7g8JVGNCICA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:03.270282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02316","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285","sha256:e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f"],"state_sha256":"2090d6597d9c61b2fc44846cf0314d8fd7c127e2e3d61ec570eb68d1b4993d89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQKmS21gY7+T62BrjZ+KHz7sQPLQ+HRKGiB6naIagL1H3dHftQLueEejyN9r8Q0GdTG3EhdM57dFD+498nU8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:29:16.410403Z","bundle_sha256":"4b97d604710d463a346e3cb27757b3343e431445803910715371c14345de134d"}}