{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3LLEX55CXQLVWLWWUG7HWVQ3DR","short_pith_number":"pith:3LLEX55C","canonical_record":{"source":{"id":"2412.15525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:31:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1285f6e38d6761ad49e75901514af8d97d8f2e1147aecf959c9fe37626ed8c6","abstract_canon_sha256":"8bf4be17ec48214d28e79db32c09b7ee821dd4822087b18bcdee612968a13e3a"},"schema_version":"1.0"},"canonical_sha256":"dad64bf7a2bc175b2ed6a1be7b561b1c6dca2a742b40de879aee5e1bd223b5a1","source":{"kind":"arxiv","id":"2412.15525","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15525","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15525v1","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15525","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"3LLEX55CXQLV","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"3LLEX55CXQLVWLWW","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"3LLEX55C","created_at":"2026-07-05T09:52:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3LLEX55CXQLVWLWWUG7HWVQ3DR","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:31:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1285f6e38d6761ad49e75901514af8d97d8f2e1147aecf959c9fe37626ed8c6","abstract_canon_sha256":"8bf4be17ec48214d28e79db32c09b7ee821dd4822087b18bcdee612968a13e3a"},"schema_version":"1.0"},"canonical_sha256":"dad64bf7a2bc175b2ed6a1be7b561b1c6dca2a742b40de879aee5e1bd223b5a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:24.635838Z","signature_b64":"7cIEUNPv3NItUEA8Jeug1pmuxOkaVl6wpMetebwSftghtG6sO8mb07fvNjGKC13+ZApw5FDu5/ACZYeTXl3GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad64bf7a2bc175b2ed6a1be7b561b1c6dca2a742b40de879aee5e1bd223b5a1","last_reissued_at":"2026-07-05T09:52:24.635408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:24.635408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15525","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":"2026-07-05T09:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vNmIoWFWhVpUHR+UO3pl3l2xh7cjY3DQDa5RnDa/5fBZg28ZMR8U++msYFI4MTCuU2fGemaZR1yoq5WJBEACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:13:52.291559Z"},"content_sha256":"263b902c3119fd006d1bbe2f597bc028629bc68c60e2adedd21f5ead04455880","schema_version":"1.0","event_id":"sha256:263b902c3119fd006d1bbe2f597bc028629bc68c60e2adedd21f5ead04455880"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3LLEX55CXQLVWLWWUG7HWVQ3DR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Back-Stepping Experience Replay in Sparse-Reward Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guwen Lyu, Masahiro Sato","submitted_at":"2024-12-20T03:31:23Z","abstract_excerpt":"Back-stepping experience replay (BER) is a reinforcement learning technique that can accelerate learning efficiency in reversible environments. BER trains an agent with generated back-stepping transitions of collected experiences and normal forward transitions. However, the original algorithm is designed for a dense-reward environment that does not require complex exploration, limiting the BER technique to demonstrate its full potential. Herein, we propose an enhanced version of BER called Generalized BER (GBER), which extends the original algorithm to sparse-reward environments, particularly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15525","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/2412.15525/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":"2026-07-05T09:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wr+9U2LsciD+Qu+8zqGhxouGAouLYg1URRqFfPlwUmOodyFE1DZjS1H58Mq16z4dHkUzq5PGPvTZ+ORJe0YdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:13:52.292062Z"},"content_sha256":"7cb7cea24fe0839463d529ebc8fd0ad745676a138a83ab52ef67f3509d379fec","schema_version":"1.0","event_id":"sha256:7cb7cea24fe0839463d529ebc8fd0ad745676a138a83ab52ef67f3509d379fec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/bundle.json","state_url":"https://pith.science/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/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":"2026-08-11T20:13:52Z","links":{"resolver":"https://pith.science/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR","bundle":"https://pith.science/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/bundle.json","state":"https://pith.science/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LLEX55CXQLVWLWWUG7HWVQ3DR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LLEX55CXQLVWLWWUG7HWVQ3DR","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":"8bf4be17ec48214d28e79db32c09b7ee821dd4822087b18bcdee612968a13e3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:31:23Z","title_canon_sha256":"e1285f6e38d6761ad49e75901514af8d97d8f2e1147aecf959c9fe37626ed8c6"},"schema_version":"1.0","source":{"id":"2412.15525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15525","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15525v1","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15525","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"3LLEX55CXQLV","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"3LLEX55CXQLVWLWW","created_at":"2026-07-05T09:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"3LLEX55C","created_at":"2026-07-05T09:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:7cb7cea24fe0839463d529ebc8fd0ad745676a138a83ab52ef67f3509d379fec","target":"graph","created_at":"2026-07-05T09:52:24Z","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/2412.15525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Back-stepping experience replay (BER) is a reinforcement learning technique that can accelerate learning efficiency in reversible environments. BER trains an agent with generated back-stepping transitions of collected experiences and normal forward transitions. However, the original algorithm is designed for a dense-reward environment that does not require complex exploration, limiting the BER technique to demonstrate its full potential. Herein, we propose an enhanced version of BER called Generalized BER (GBER), which extends the original algorithm to sparse-reward environments, particularly ","authors_text":"Guwen Lyu, Masahiro Sato","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:31:23Z","title":"Generalized Back-Stepping Experience Replay in Sparse-Reward Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15525","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":"sha256:263b902c3119fd006d1bbe2f597bc028629bc68c60e2adedd21f5ead04455880","target":"record","created_at":"2026-07-05T09:52:24Z","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":"8bf4be17ec48214d28e79db32c09b7ee821dd4822087b18bcdee612968a13e3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:31:23Z","title_canon_sha256":"e1285f6e38d6761ad49e75901514af8d97d8f2e1147aecf959c9fe37626ed8c6"},"schema_version":"1.0","source":{"id":"2412.15525","kind":"arxiv","version":1}},"canonical_sha256":"dad64bf7a2bc175b2ed6a1be7b561b1c6dca2a742b40de879aee5e1bd223b5a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad64bf7a2bc175b2ed6a1be7b561b1c6dca2a742b40de879aee5e1bd223b5a1","first_computed_at":"2026-07-05T09:52:24.635408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:24.635408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cIEUNPv3NItUEA8Jeug1pmuxOkaVl6wpMetebwSftghtG6sO8mb07fvNjGKC13+ZApw5FDu5/ACZYeTXl3GDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:24.635838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:263b902c3119fd006d1bbe2f597bc028629bc68c60e2adedd21f5ead04455880","sha256:7cb7cea24fe0839463d529ebc8fd0ad745676a138a83ab52ef67f3509d379fec"],"state_sha256":"5f35ec9c982440e5960bca4d457461adede9eba0d29cfe5a4cb0ffc9fd315d13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTM2JYLj3GE7wh8QFJOZ7VONua3IxL6y1QGGV7a+WCDYtKpL8kWq7dmmRSTMsxf3dCkvbRWrjMez2AFIDHADAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:13:52.296040Z","bundle_sha256":"a8aa9c81cd17eed0a4ad8966e4a5632833622fa3a952ff25ba926d0b90a384d0"}}