{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OICWVFXJLHAXVYWTZ6NUT3LOR5","short_pith_number":"pith:OICWVFXJ","canonical_record":{"source":{"id":"2401.11372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48a7cb39849cdd8d6e3d11290a76c514c6d29d446ffc841f0b14607f018fdd12","abstract_canon_sha256":"ab3d412e6af9860b3ee8109ed11206fd71c7cc1efee1683a77aa02c6729158d8"},"schema_version":"1.0"},"canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","source":{"kind":"arxiv","id":"2401.11372","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11372","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11372v2","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11372","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"OICWVFXJLHAX","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"OICWVFXJLHAXVYWT","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"OICWVFXJ","created_at":"2026-07-05T09:10:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OICWVFXJLHAXVYWTZ6NUT3LOR5","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48a7cb39849cdd8d6e3d11290a76c514c6d29d446ffc841f0b14607f018fdd12","abstract_canon_sha256":"ab3d412e6af9860b3ee8109ed11206fd71c7cc1efee1683a77aa02c6729158d8"},"schema_version":"1.0"},"canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:45.077730Z","signature_b64":"Hk/bpImRnTLpK7GY7SYMOA2HgDQnRVxvJ9w6QPxDaKycwza6727NPcjkR0RvqNzdwD+Kqa4UvO4jhR9aXprcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","last_reissued_at":"2026-07-05T09:10:45.077324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:45.077324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11372","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":"2026-07-05T09:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cc5xCM2WHgDQTmYWvftcn14F3+lOGsomtoctRWrgDJa4Eddd0dXaBlDFug5py4c/Q937K8dBW5BKdlF8ZQ/TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:59:43.991293Z"},"content_sha256":"4a293dbdbcf3c324cad485f51a0e9bb4d7e621fcf831afea772b28273fc0f515","schema_version":"1.0","event_id":"sha256:4a293dbdbcf3c324cad485f51a0e9bb4d7e621fcf831afea772b28273fc0f515"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OICWVFXJLHAXVYWTZ6NUT3LOR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dong Chen, Xiaobo Tan, Xinda Qi, Zhaojian Li","submitted_at":"2024-01-21T02:17:16Z","abstract_excerpt":"In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate reversibility, reducing the need for complex reward shaping. The method constructs reversed trajectories using back-stepping transitions to reach random or fixed targets. Interpretable as a bi-directional approach, BER addresses inaccuracies in back-stepping transitions through a distillation of the replay experience during learning. Given the intricate nature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11372","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/2401.11372/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":"2026-07-05T09:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Js9VlFQTbGebopW3K5Qq5jZhLZPAGpSgWM2G42L7oKuTnIKM6kaXquxy8nW/NfNp4C7clSQSO6AvK3H6zkxVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:59:43.991960Z"},"content_sha256":"3a519ee0d03fded5e4f9e3dae6f46774c882fa4fd0516cc3d395a1dfd180e49b","schema_version":"1.0","event_id":"sha256:3a519ee0d03fded5e4f9e3dae6f46774c882fa4fd0516cc3d395a1dfd180e49b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/bundle.json","state_url":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/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":"2026-08-12T04:59:43Z","links":{"resolver":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5","bundle":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/bundle.json","state":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OICWVFXJLHAXVYWTZ6NUT3LOR5","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":"ab3d412e6af9860b3ee8109ed11206fd71c7cc1efee1683a77aa02c6729158d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","title_canon_sha256":"48a7cb39849cdd8d6e3d11290a76c514c6d29d446ffc841f0b14607f018fdd12"},"schema_version":"1.0","source":{"id":"2401.11372","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11372","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11372v2","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11372","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"OICWVFXJLHAX","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"OICWVFXJLHAXVYWT","created_at":"2026-07-05T09:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"OICWVFXJ","created_at":"2026-07-05T09:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:3a519ee0d03fded5e4f9e3dae6f46774c882fa4fd0516cc3d395a1dfd180e49b","target":"graph","created_at":"2026-07-05T09:10:45Z","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/2401.11372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate reversibility, reducing the need for complex reward shaping. The method constructs reversed trajectories using back-stepping transitions to reach random or fixed targets. Interpretable as a bi-directional approach, BER addresses inaccuracies in back-stepping transitions through a distillation of the replay experience during learning. Given the intricate nature ","authors_text":"Dong Chen, Xiaobo Tan, Xinda Qi, Zhaojian Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","title":"Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11372","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":"sha256:4a293dbdbcf3c324cad485f51a0e9bb4d7e621fcf831afea772b28273fc0f515","target":"record","created_at":"2026-07-05T09:10:45Z","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":"ab3d412e6af9860b3ee8109ed11206fd71c7cc1efee1683a77aa02c6729158d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","title_canon_sha256":"48a7cb39849cdd8d6e3d11290a76c514c6d29d446ffc841f0b14607f018fdd12"},"schema_version":"1.0","source":{"id":"2401.11372","kind":"arxiv","version":2}},"canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","first_computed_at":"2026-07-05T09:10:45.077324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:45.077324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hk/bpImRnTLpK7GY7SYMOA2HgDQnRVxvJ9w6QPxDaKycwza6727NPcjkR0RvqNzdwD+Kqa4UvO4jhR9aXprcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:45.077730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11372","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a293dbdbcf3c324cad485f51a0e9bb4d7e621fcf831afea772b28273fc0f515","sha256:3a519ee0d03fded5e4f9e3dae6f46774c882fa4fd0516cc3d395a1dfd180e49b"],"state_sha256":"3a25b46c78ee8d7a063ec49b9c89cf0760bc906d6bb62ece46d017ee0ea3cd71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4tZEJeEUUSL8go06dIjaoO7iacxRnQDBGEaLljwIL0mg8Kzyqk5/Pkou15iS7Xb3l7eTI87acIhyFIdmOgZ0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T04:59:43.997195Z","bundle_sha256":"109e20b8ef299c47df8ddb2ed76724b7cdbdc500bca543c8d79a22d4e659b51b"}}