{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7G7HACKSE7M2RMHUCIEGR6YPNP","short_pith_number":"pith:7G7HACKS","canonical_record":{"source":{"id":"2311.17565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80","abstract_canon_sha256":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d"},"schema_version":"1.0"},"canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","source":{"kind":"arxiv","id":"2311.17565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17565v1","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_12","alias_value":"7G7HACKSE7M2","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_16","alias_value":"7G7HACKSE7M2RMHU","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_8","alias_value":"7G7HACKS","created_at":"2026-07-05T07:18:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7G7HACKSE7M2RMHUCIEGR6YPNP","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80","abstract_canon_sha256":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d"},"schema_version":"1.0"},"canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:15.590786Z","signature_b64":"8PxV5ghaALj0PiEVhzkcGNbWXo8bYlwc0iK2whD6pINd8Njoj5GIuY6tc+HwYsx3P+DigvZg9APb/RwwQP1hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","last_reissued_at":"2026-07-05T07:18:15.590300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:15.590300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17565","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":"2026-07-05T07:18:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jxMVPlSSaME3f+TUoMgbpHrxD86bsaBgPqXScTWWWDDTrQdCCN7MBQsRzDd2H1uIG6DfYfOLB9zyF/8KSFiTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:07:05.760854Z"},"content_sha256":"31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0","schema_version":"1.0","event_id":"sha256:31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7G7HACKSE7M2RMHUCIEGR6YPNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ke Chen, Lisheng Wu","submitted_at":"2023-11-29T11:59:03Z","abstract_excerpt":"In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target values. This paper dives deep into these biases, categorizing them into two distinct categories: \"shooting\" and \"shifting\". Recognizing that certain behavior policies can hasten policy refinement, we present solutions designed to capitalize on the positive aspects of these biases while minimizing their drawbacks, enabling the use of larger step sizes to speed up"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17565","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/2311.17565/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":"2026-07-05T07:18:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDplIpvSrWHUQ9etGUvP1MTXJZ8k+lrBYVMvwe/Nji/LdF70arBtuZzuEtYUcKdaualFJjuS99eehjX4T6CtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:07:05.761182Z"},"content_sha256":"06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3","schema_version":"1.0","event_id":"sha256:06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/bundle.json","state_url":"https://pith.science/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/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":"2026-08-13T16:07:05Z","links":{"resolver":"https://pith.science/pith/7G7HACKSE7M2RMHUCIEGR6YPNP","bundle":"https://pith.science/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/bundle.json","state":"https://pith.science/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7G7HACKSE7M2RMHUCIEGR6YPNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7G7HACKSE7M2RMHUCIEGR6YPNP","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":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80"},"schema_version":"1.0","source":{"id":"2311.17565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17565v1","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_12","alias_value":"7G7HACKSE7M2","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_16","alias_value":"7G7HACKSE7M2RMHU","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_8","alias_value":"7G7HACKS","created_at":"2026-07-05T07:18:15Z"}],"graph_snapshots":[{"event_id":"sha256:06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3","target":"graph","created_at":"2026-07-05T07:18:15Z","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/2311.17565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target values. This paper dives deep into these biases, categorizing them into two distinct categories: \"shooting\" and \"shifting\". Recognizing that certain behavior policies can hasten policy refinement, we present solutions designed to capitalize on the positive aspects of these biases while minimizing their drawbacks, enabling the use of larger step sizes to speed up","authors_text":"Ke Chen, Lisheng Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17565","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":"sha256:31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0","target":"record","created_at":"2026-07-05T07:18:15Z","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":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80"},"schema_version":"1.0","source":{"id":"2311.17565","kind":"arxiv","version":1}},"canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","first_computed_at":"2026-07-05T07:18:15.590300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:15.590300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8PxV5ghaALj0PiEVhzkcGNbWXo8bYlwc0iK2whD6pINd8Njoj5GIuY6tc+HwYsx3P+DigvZg9APb/RwwQP1hBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:15.590786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0","sha256:06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3"],"state_sha256":"d1e90a485c5e651b7d212d14d2a8271d16d89df28b0103fcc39c819203d5e8f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zdxghfl9aFkBl8B7EfRpSL7/0zk/iiAPDSo/xv7OmsRuzxIX6XmCsftKSRzOnjk5mmSkJ85uyIXhGdzHiW4vBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:07:05.765442Z","bundle_sha256":"0a2605756e2c7add7413ccbdbc4d59926ded760687157bd4d2d1acb468fd784a"}}