{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","short_pith_number":"pith:QF3DGSQF","canonical_record":{"source":{"id":"2411.14913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc","abstract_canon_sha256":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed"},"schema_version":"1.0"},"canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","source":{"kind":"arxiv","id":"2411.14913","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14913v2","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"QF3DGSQFE23E","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"QF3DGSQFE23EU4FX","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"QF3DGSQF","created_at":"2026-07-05T10:54:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc","abstract_canon_sha256":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed"},"schema_version":"1.0"},"canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:14.053810Z","signature_b64":"n3HlAxZspOSS8WnOxLYauRUpdhwblWHeEZ+fQUVHtFx9RQdeJ7GTH9YmIFps1OWpFZEBfzpuYEF1m9Y+IfDfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","last_reissued_at":"2026-07-05T10:54:14.053307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:14.053307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14913","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":"2026-07-05T10:54:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/ite5326e0bAYwtQZSQcUMPZX+IhSfAjNE6HbqrGKgOpTB3J5dQyzVQLc6SjsWHGPeWIeoTwTKuqgR/dgBeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:03:02.653087Z"},"content_sha256":"c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577","schema_version":"1.0","event_id":"sha256:c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gerhard Neumann, Huy Le, Miroslav Gabriel, Ngo Anh Vien, Tai Hoang","submitted_at":"2024-11-22T13:14:54Z","abstract_excerpt":"Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid framework that tackles both discrete and continuous action spaces. First, we model the continuous motion parameter policy as a diffusion model, and second, we incorporate this into a maximum entropy reinforcement learning framework that unifies both the discrete and continuous components. The discrete action space, such as contact point selection, is optimized thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14913","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/2411.14913/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":"2026-07-05T10:54:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znHo95qufMeSjfuLWKox/aEtHHcgKH0RUCbXzGK9aXqMDTTGfeQ1BgIf3N2RG1GDB3Go6kVNCi5RgGSPdJlmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:03:02.653592Z"},"content_sha256":"0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a","schema_version":"1.0","event_id":"sha256:0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/bundle.json","state_url":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/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":"2026-08-12T21:03:02Z","links":{"resolver":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC","bundle":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/bundle.json","state":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","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":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc"},"schema_version":"1.0","source":{"id":"2411.14913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14913v2","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"QF3DGSQFE23E","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"QF3DGSQFE23EU4FX","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"QF3DGSQF","created_at":"2026-07-05T10:54:14Z"}],"graph_snapshots":[{"event_id":"sha256:0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a","target":"graph","created_at":"2026-07-05T10:54:14Z","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/2411.14913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid framework that tackles both discrete and continuous action spaces. First, we model the continuous motion parameter policy as a diffusion model, and second, we incorporate this into a maximum entropy reinforcement learning framework that unifies both the discrete and continuous components. The discrete action space, such as contact point selection, is optimized thr","authors_text":"Gerhard Neumann, Huy Le, Miroslav Gabriel, Ngo Anh Vien, Tai Hoang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14913","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:c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577","target":"record","created_at":"2026-07-05T10:54:14Z","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":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc"},"schema_version":"1.0","source":{"id":"2411.14913","kind":"arxiv","version":2}},"canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","first_computed_at":"2026-07-05T10:54:14.053307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:14.053307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n3HlAxZspOSS8WnOxLYauRUpdhwblWHeEZ+fQUVHtFx9RQdeJ7GTH9YmIFps1OWpFZEBfzpuYEF1m9Y+IfDfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:14.053810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577","sha256:0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a"],"state_sha256":"cb34e2dbe89e2191394de797cb328ce725a3604c0553ed7b21f0993f632a4bc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCe/T68l0amhTPX3B9lshwzkIaqu1l8dA/MTVGo1pRNuzAxQcnDj12RGs+lelJrdoSyBs8PJFVnPj576fC+oAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:03:02.658505Z","bundle_sha256":"6739b4d6d1fe1cff0340f764f5e17f2e0f05f86333c6bc8520b1b35c0b28472b"}}