{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AZOMBBCHNG4ZQ2QSRC65OM2XFA","short_pith_number":"pith:AZOMBBCH","canonical_record":{"source":{"id":"2503.05833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T12:52:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0cd04235e144effab37a7c30bdc28e15bc80cb29223d9604c828a6a71128a2dc","abstract_canon_sha256":"1af16f46a698e5a053c14c07537d516cb71a7e7ad32ebf8063e7e1ce58f438b0"},"schema_version":"1.0"},"canonical_sha256":"065cc0844769b9986a1288bdd73357282eebc1b82d79cee8e1da7419ac08f39a","source":{"kind":"arxiv","id":"2503.05833","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05833","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05833v2","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05833","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"AZOMBBCHNG4Z","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"AZOMBBCHNG4ZQ2QS","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"AZOMBBCH","created_at":"2026-07-05T11:48:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AZOMBBCHNG4ZQ2QSRC65OM2XFA","target":"record","payload":{"canonical_record":{"source":{"id":"2503.05833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T12:52:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0cd04235e144effab37a7c30bdc28e15bc80cb29223d9604c828a6a71128a2dc","abstract_canon_sha256":"1af16f46a698e5a053c14c07537d516cb71a7e7ad32ebf8063e7e1ce58f438b0"},"schema_version":"1.0"},"canonical_sha256":"065cc0844769b9986a1288bdd73357282eebc1b82d79cee8e1da7419ac08f39a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:01.646301Z","signature_b64":"GcIFbU3FaDKoy4PZ87YYbT1w9cpeHeqj0z5ewiow4dPKLVtcT7ujdHOVBTAXpagwoCori/6gFu5D5Pjvtc21Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065cc0844769b9986a1288bdd73357282eebc1b82d79cee8e1da7419ac08f39a","last_reissued_at":"2026-07-05T11:48:01.645764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:01.645764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.05833","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":"2026-07-05T11:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Ln2KPHQp5gbyllCAsAywx+r5jg5VZaa5BrL/Tsr7GS7LVrYYjPJOTNou7Q7RoSe4OYqjrp+3RijLM/leV5qBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:13:44.466812Z"},"content_sha256":"aa6de1c3cb4855c14196941dac24dfba8ebceb8abc54e00c8fd671d303ac3f14","schema_version":"1.0","event_id":"sha256:aa6de1c3cb4855c14196941dac24dfba8ebceb8abc54e00c8fd671d303ac3f14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AZOMBBCHNG4ZQ2QSRC65OM2XFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refined Policy Distillation: From VLA Generalists to RL Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Florian Walter, Tobias J\\\"ulg, Wolfram Burgard","submitted_at":"2025-03-06T12:52:11Z","abstract_excerpt":"Vision-Language-Action Models (VLAs) have demonstrated remarkable generalization capabilities in real-world experiments. However, their success rates are often not on par with expert policies, and they require fine-tuning when the setup changes. In this work, we introduce Refined Policy Distillation (RPD), a novel Reinforcement Learning (RL)-based policy refinement method that bridges this performance gap through a combination of on-policy RL with behavioral cloning. The core idea of RPD is to distill and refine VLAs into compact, high-performing expert policies by guiding the student policy d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05833","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/2503.05833/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":"2026-07-05T11:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DhKxI+o4Pz7Ks85R0Y4e41QWHiWSaKaBkFZo1XpZs92rUhFyOd8CvLc402s/bMnZ67uGQuQm9Y2Z6w5skpk1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:13:44.467308Z"},"content_sha256":"6c28b397194e2bb48cb8e5cf82e9dc35ce9581e87a3321556f04f3cd5268db54","schema_version":"1.0","event_id":"sha256:6c28b397194e2bb48cb8e5cf82e9dc35ce9581e87a3321556f04f3cd5268db54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/bundle.json","state_url":"https://pith.science/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/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":"2026-08-07T10:13:44Z","links":{"resolver":"https://pith.science/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA","bundle":"https://pith.science/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/bundle.json","state":"https://pith.science/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZOMBBCHNG4ZQ2QSRC65OM2XFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AZOMBBCHNG4ZQ2QSRC65OM2XFA","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":"1af16f46a698e5a053c14c07537d516cb71a7e7ad32ebf8063e7e1ce58f438b0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T12:52:11Z","title_canon_sha256":"0cd04235e144effab37a7c30bdc28e15bc80cb29223d9604c828a6a71128a2dc"},"schema_version":"1.0","source":{"id":"2503.05833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05833","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05833v2","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05833","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"AZOMBBCHNG4Z","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"AZOMBBCHNG4ZQ2QS","created_at":"2026-07-05T11:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"AZOMBBCH","created_at":"2026-07-05T11:48:01Z"}],"graph_snapshots":[{"event_id":"sha256:6c28b397194e2bb48cb8e5cf82e9dc35ce9581e87a3321556f04f3cd5268db54","target":"graph","created_at":"2026-07-05T11:48:01Z","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/2503.05833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action Models (VLAs) have demonstrated remarkable generalization capabilities in real-world experiments. However, their success rates are often not on par with expert policies, and they require fine-tuning when the setup changes. In this work, we introduce Refined Policy Distillation (RPD), a novel Reinforcement Learning (RL)-based policy refinement method that bridges this performance gap through a combination of on-policy RL with behavioral cloning. The core idea of RPD is to distill and refine VLAs into compact, high-performing expert policies by guiding the student policy d","authors_text":"Florian Walter, Tobias J\\\"ulg, Wolfram Burgard","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T12:52:11Z","title":"Refined Policy Distillation: From VLA Generalists to RL Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05833","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:aa6de1c3cb4855c14196941dac24dfba8ebceb8abc54e00c8fd671d303ac3f14","target":"record","created_at":"2026-07-05T11:48:01Z","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":"1af16f46a698e5a053c14c07537d516cb71a7e7ad32ebf8063e7e1ce58f438b0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T12:52:11Z","title_canon_sha256":"0cd04235e144effab37a7c30bdc28e15bc80cb29223d9604c828a6a71128a2dc"},"schema_version":"1.0","source":{"id":"2503.05833","kind":"arxiv","version":2}},"canonical_sha256":"065cc0844769b9986a1288bdd73357282eebc1b82d79cee8e1da7419ac08f39a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065cc0844769b9986a1288bdd73357282eebc1b82d79cee8e1da7419ac08f39a","first_computed_at":"2026-07-05T11:48:01.645764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:01.645764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GcIFbU3FaDKoy4PZ87YYbT1w9cpeHeqj0z5ewiow4dPKLVtcT7ujdHOVBTAXpagwoCori/6gFu5D5Pjvtc21Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:01.646301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa6de1c3cb4855c14196941dac24dfba8ebceb8abc54e00c8fd671d303ac3f14","sha256:6c28b397194e2bb48cb8e5cf82e9dc35ce9581e87a3321556f04f3cd5268db54"],"state_sha256":"b1d57938c16732d840ebe636b68321eab35fb4777edb9ee2713ea24445beed58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"He2T9hJKHmRrGJT+VnmJzk8Ob0ILtup1w0QPyU0RCRf9J3nkG/WgriD9Y8BzJWOEBHvbD+1BXJgVw8D/jxPECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:13:44.471638Z","bundle_sha256":"6e33a93368b42a56d8e565e192945d33f9c0fdf2a5ef8044c1d25dd827eda29a"}}