{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FDVJGFOH6YWZL6O7XUCFQ2IOKX","short_pith_number":"pith:FDVJGFOH","canonical_record":{"source":{"id":"2201.00354","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-02T13:09:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7ef82c97e58c8000f6878da03adcb98dda687632e35db87e98eab93ccc67e9a","abstract_canon_sha256":"6fb2e1adcedcad38d0263a1cd68f522879e3ada6d7320f657c4434ef27bec863"},"schema_version":"1.0"},"canonical_sha256":"28ea9315c7f62d95f9dfbd0458690e55e544bc854d35e54196e6c5de5020111b","source":{"kind":"arxiv","id":"2201.00354","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00354","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00354v2","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00354","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"FDVJGFOH6YWZ","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"FDVJGFOH6YWZL6O7","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"FDVJGFOH","created_at":"2026-07-05T05:11:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FDVJGFOH6YWZL6O7XUCFQ2IOKX","target":"record","payload":{"canonical_record":{"source":{"id":"2201.00354","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-02T13:09:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7ef82c97e58c8000f6878da03adcb98dda687632e35db87e98eab93ccc67e9a","abstract_canon_sha256":"6fb2e1adcedcad38d0263a1cd68f522879e3ada6d7320f657c4434ef27bec863"},"schema_version":"1.0"},"canonical_sha256":"28ea9315c7f62d95f9dfbd0458690e55e544bc854d35e54196e6c5de5020111b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:36.296527Z","signature_b64":"yYocCJgwGBUQ/yW0dsBA4EIuksx8GAcO0Vs8ZEaCWVBYO1PZiRRAOmgJEodPjiNlK5+ITLSre1HN4HojVlQgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ea9315c7f62d95f9dfbd0458690e55e544bc854d35e54196e6c5de5020111b","last_reissued_at":"2026-07-05T05:11:36.296040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:36.296040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.00354","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":"2026-07-05T05:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjnGmMhGBRREsfno7j8sj4/iIHw0ofJvmWAtiVgvjKmsLAcQFXIBAXEnImJD+jp51kuIO0ucs5gG9gRofduLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:04:56.063093Z"},"content_sha256":"6b52675d7fd77d099c8a5a4102741082efb06c5d294c9e06ff740bd4e9b70db4","schema_version":"1.0","event_id":"sha256:6b52675d7fd77d099c8a5a4102741082efb06c5d294c9e06ff740bd4e9b70db4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FDVJGFOH6YWZL6O7XUCFQ2IOKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Sun, Taiyi Wang","submitted_at":"2022-01-02T13:09:40Z","abstract_excerpt":"Although it is well known that exploration plays a key role in Reinforcement Learning (RL), prevailing exploration strategies for continuous control tasks in RL are mainly based on naive isotropic Gaussian noise regardless of the causality relationship between action space and the task and consider all dimensions of actions equally important. In this work, we propose to conduct interventions on the primal action space to discover the causal relationship between the action space and the task reward. We propose the method of State-Wise Action Refined (SWAR), which addresses the issue of action s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00354","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/2201.00354/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":"2026-07-05T05:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwXWl4IUAqWFmsNQwwzc9WnVLzwShNUyCEjw8UXteYCeQodlT+Ycl7wqOcxqr04RaMQTVFJ3/nDpcYwDd9tYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:04:56.063620Z"},"content_sha256":"51c1127df189893cf1cc830cabf88e6d62a1f53b638d1fdba35d0bf4c22a8620","schema_version":"1.0","event_id":"sha256:51c1127df189893cf1cc830cabf88e6d62a1f53b638d1fdba35d0bf4c22a8620"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/bundle.json","state_url":"https://pith.science/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/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":"2026-08-04T17:04:56Z","links":{"resolver":"https://pith.science/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX","bundle":"https://pith.science/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/bundle.json","state":"https://pith.science/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDVJGFOH6YWZL6O7XUCFQ2IOKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FDVJGFOH6YWZL6O7XUCFQ2IOKX","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":"6fb2e1adcedcad38d0263a1cd68f522879e3ada6d7320f657c4434ef27bec863","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-02T13:09:40Z","title_canon_sha256":"b7ef82c97e58c8000f6878da03adcb98dda687632e35db87e98eab93ccc67e9a"},"schema_version":"1.0","source":{"id":"2201.00354","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00354","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00354v2","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00354","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"FDVJGFOH6YWZ","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"FDVJGFOH6YWZL6O7","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"FDVJGFOH","created_at":"2026-07-05T05:11:36Z"}],"graph_snapshots":[{"event_id":"sha256:51c1127df189893cf1cc830cabf88e6d62a1f53b638d1fdba35d0bf4c22a8620","target":"graph","created_at":"2026-07-05T05:11:36Z","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/2201.00354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although it is well known that exploration plays a key role in Reinforcement Learning (RL), prevailing exploration strategies for continuous control tasks in RL are mainly based on naive isotropic Gaussian noise regardless of the causality relationship between action space and the task and consider all dimensions of actions equally important. In this work, we propose to conduct interventions on the primal action space to discover the causal relationship between the action space and the task reward. We propose the method of State-Wise Action Refined (SWAR), which addresses the issue of action s","authors_text":"Hao Sun, Taiyi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-02T13:09:40Z","title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00354","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":"sha256:6b52675d7fd77d099c8a5a4102741082efb06c5d294c9e06ff740bd4e9b70db4","target":"record","created_at":"2026-07-05T05:11:36Z","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":"6fb2e1adcedcad38d0263a1cd68f522879e3ada6d7320f657c4434ef27bec863","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-02T13:09:40Z","title_canon_sha256":"b7ef82c97e58c8000f6878da03adcb98dda687632e35db87e98eab93ccc67e9a"},"schema_version":"1.0","source":{"id":"2201.00354","kind":"arxiv","version":2}},"canonical_sha256":"28ea9315c7f62d95f9dfbd0458690e55e544bc854d35e54196e6c5de5020111b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ea9315c7f62d95f9dfbd0458690e55e544bc854d35e54196e6c5de5020111b","first_computed_at":"2026-07-05T05:11:36.296040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:36.296040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYocCJgwGBUQ/yW0dsBA4EIuksx8GAcO0Vs8ZEaCWVBYO1PZiRRAOmgJEodPjiNlK5+ITLSre1HN4HojVlQgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:36.296527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00354","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b52675d7fd77d099c8a5a4102741082efb06c5d294c9e06ff740bd4e9b70db4","sha256:51c1127df189893cf1cc830cabf88e6d62a1f53b638d1fdba35d0bf4c22a8620"],"state_sha256":"4a61192e2cbb3ea47f8fbeb0a3a79796af647793720de18adeaca9c75eb1d692"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/b/3h7T4t1J+47ewB+9YHgmo1VwHRQEkUdJrbwBEUDyuECPnRwKGcO4SmIc6WIJ1Yc97jyjbqjRHbfG9D7blCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:04:56.067122Z","bundle_sha256":"fd8f4701113c4c9d616ef5564cf1b96700f561a47a4e472b24398b19d00ca33f"}}