{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BL74AFZ243J6THCSCPCHRDONTB","short_pith_number":"pith:BL74AFZ2","canonical_record":{"source":{"id":"2412.09858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T04:57:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"27f1fa792f324fdb0f33b208cdd8692b38a1852190adeca60bce9ae443595d98","abstract_canon_sha256":"d6fd22e3bc45d570e970159c9a0ae0a532e46141d47a8396abdaf48d71f113a2"},"schema_version":"1.0"},"canonical_sha256":"0affc0173ae6d3e99c5213c4788dcd9851fd75c090c40119f83b4bfa8fcf84cf","source":{"kind":"arxiv","id":"2412.09858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09858","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09858v1","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09858","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"BL74AFZ243J6","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"BL74AFZ243J6THCS","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"BL74AFZ2","created_at":"2026-07-05T09:48:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BL74AFZ243J6THCSCPCHRDONTB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T04:57:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"27f1fa792f324fdb0f33b208cdd8692b38a1852190adeca60bce9ae443595d98","abstract_canon_sha256":"d6fd22e3bc45d570e970159c9a0ae0a532e46141d47a8396abdaf48d71f113a2"},"schema_version":"1.0"},"canonical_sha256":"0affc0173ae6d3e99c5213c4788dcd9851fd75c090c40119f83b4bfa8fcf84cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:42.772263Z","signature_b64":"o29rGfUjHgoLXhKazh2z460BpkzooeH0LgMPNyqTf3SX4cygpNcMphFmL4qJTQliCe+BqK6iWcFDYJUwQzwEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0affc0173ae6d3e99c5213c4788dcd9851fd75c090c40119f83b4bfa8fcf84cf","last_reissued_at":"2026-07-05T09:48:42.771773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:42.771773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09858","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":"2026-07-05T09:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DhTJE3VApdyfbkewJCEyC7Aiv2DvOSE2xzIjTnJu7+Pax0WTZg9amaImAGYzDBDmLS/0FqDidCdfB/7yxU4XAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:02:23.809171Z"},"content_sha256":"57a9021d51b23f3677f5d0c29447e5debdd950bf51db3e06283e194fadc91fe9","schema_version":"1.0","event_id":"sha256:57a9021d51b23f3677f5d0c29447e5debdd950bf51db3e06283e194fadc91fe9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BL74AFZ243J6THCSCPCHRDONTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Charles Xu, Jianlan Luo, Qiyang Li, Sergey Levine","submitted_at":"2024-12-13T04:57:55Z","abstract_excerpt":"Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the quality of their training data. In this work, we propose Reinforcement Learning Distilled Generalists (RLDG), a method that leverages reinforcement learning to generate high-quality training data for finetuning generalist policies. Through extensive real-world experiments on precise manipulation tasks like connector insertion and assembly, we demonstrate that generalist policies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09858","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/2412.09858/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":"2026-07-05T09:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USiBHA9p83Bh/p2nPTL75z53VEHffn7lmJmVk0FUxvs6RlMB8YlUMtZTz1/w3RRml9WqC1IVlrthWu1zVe+sCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:02:23.810089Z"},"content_sha256":"bfc5645c13cac672299c651acc19206940ca0fd07772b33d028bb4f2fec01f2d","schema_version":"1.0","event_id":"sha256:bfc5645c13cac672299c651acc19206940ca0fd07772b33d028bb4f2fec01f2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BL74AFZ243J6THCSCPCHRDONTB/bundle.json","state_url":"https://pith.science/pith/BL74AFZ243J6THCSCPCHRDONTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BL74AFZ243J6THCSCPCHRDONTB/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":"2026-08-08T15:02:23Z","links":{"resolver":"https://pith.science/pith/BL74AFZ243J6THCSCPCHRDONTB","bundle":"https://pith.science/pith/BL74AFZ243J6THCSCPCHRDONTB/bundle.json","state":"https://pith.science/pith/BL74AFZ243J6THCSCPCHRDONTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BL74AFZ243J6THCSCPCHRDONTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BL74AFZ243J6THCSCPCHRDONTB","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":"d6fd22e3bc45d570e970159c9a0ae0a532e46141d47a8396abdaf48d71f113a2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T04:57:55Z","title_canon_sha256":"27f1fa792f324fdb0f33b208cdd8692b38a1852190adeca60bce9ae443595d98"},"schema_version":"1.0","source":{"id":"2412.09858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09858","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09858v1","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09858","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"BL74AFZ243J6","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"BL74AFZ243J6THCS","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"BL74AFZ2","created_at":"2026-07-05T09:48:42Z"}],"graph_snapshots":[{"event_id":"sha256:bfc5645c13cac672299c651acc19206940ca0fd07772b33d028bb4f2fec01f2d","target":"graph","created_at":"2026-07-05T09:48:42Z","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/2412.09858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the quality of their training data. In this work, we propose Reinforcement Learning Distilled Generalists (RLDG), a method that leverages reinforcement learning to generate high-quality training data for finetuning generalist policies. Through extensive real-world experiments on precise manipulation tasks like connector insertion and assembly, we demonstrate that generalist policies","authors_text":"Charles Xu, Jianlan Luo, Qiyang Li, Sergey Levine","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T04:57:55Z","title":"RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09858","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":"sha256:57a9021d51b23f3677f5d0c29447e5debdd950bf51db3e06283e194fadc91fe9","target":"record","created_at":"2026-07-05T09:48:42Z","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":"d6fd22e3bc45d570e970159c9a0ae0a532e46141d47a8396abdaf48d71f113a2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T04:57:55Z","title_canon_sha256":"27f1fa792f324fdb0f33b208cdd8692b38a1852190adeca60bce9ae443595d98"},"schema_version":"1.0","source":{"id":"2412.09858","kind":"arxiv","version":1}},"canonical_sha256":"0affc0173ae6d3e99c5213c4788dcd9851fd75c090c40119f83b4bfa8fcf84cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0affc0173ae6d3e99c5213c4788dcd9851fd75c090c40119f83b4bfa8fcf84cf","first_computed_at":"2026-07-05T09:48:42.771773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:42.771773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o29rGfUjHgoLXhKazh2z460BpkzooeH0LgMPNyqTf3SX4cygpNcMphFmL4qJTQliCe+BqK6iWcFDYJUwQzwEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:42.772263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57a9021d51b23f3677f5d0c29447e5debdd950bf51db3e06283e194fadc91fe9","sha256:bfc5645c13cac672299c651acc19206940ca0fd07772b33d028bb4f2fec01f2d"],"state_sha256":"04fc88a1bacf6b16d77f0392f31f01ddbb265edd889ad1b660a9312293535a85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wblSwAj4eQ5MdaJ93fr3fNfJPPmJ59DF0bpjWhxAJCrIR0BTEy4TA1sgaAShTiHEXhrjMk3sqfGpvQCyEbNECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:02:23.816605Z","bundle_sha256":"6940e9b1f7b0167e4da96a22756ffd507a936224404fe278ecc5ef71b7878b9b"}}