{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A5XYM4CSJ4UYVV7S3SDJ7XBR2M","short_pith_number":"pith:A5XYM4CS","canonical_record":{"source":{"id":"2402.14528","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d39d64654c292ca7d196f82488edd602943d91ab6a4fa8aa27c7244386e6d0da","abstract_canon_sha256":"cd4b19b476184bae4701dbfae483aa83779ba56a5c8f9b3ab076a5c3e8b25bb6"},"schema_version":"1.0"},"canonical_sha256":"076f8670524f298ad7f2dc869fdc31d3164a995f28c06209592a7b30ec5f2ea3","source":{"kind":"arxiv","id":"2402.14528","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14528","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14528v5","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14528","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"A5XYM4CSJ4UY","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"A5XYM4CSJ4UYVV7S","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"A5XYM4CS","created_at":"2026-07-05T09:30:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A5XYM4CSJ4UYVV7S3SDJ7XBR2M","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14528","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d39d64654c292ca7d196f82488edd602943d91ab6a4fa8aa27c7244386e6d0da","abstract_canon_sha256":"cd4b19b476184bae4701dbfae483aa83779ba56a5c8f9b3ab076a5c3e8b25bb6"},"schema_version":"1.0"},"canonical_sha256":"076f8670524f298ad7f2dc869fdc31d3164a995f28c06209592a7b30ec5f2ea3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:08.531024Z","signature_b64":"VheWimG961ruJ7okoXfWOLB5Jd6iwcLq+jzIxQuLqWkgVImfbgvHYSRDLVauDCUjwtaGio0y172i4/vz1RA9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076f8670524f298ad7f2dc869fdc31d3164a995f28c06209592a7b30ec5f2ea3","last_reissued_at":"2026-07-05T09:30:08.530545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:08.530545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14528","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5/1pwCLdcXQNwI71X9yi4dy48SSIEJ54tfVSnN9ql1laoz0QSEXrDpyNqqKOXTN9z3Xg8k+0rFEwZ0IgfLszCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:57:25.855813Z"},"content_sha256":"2c9cd6baaaf9612c8aa1db8e4c9d5fe7b6c9824011c4d97b57aaa97f24d41d82","schema_version":"1.0","event_id":"sha256:2c9cd6baaaf9612c8aa1db8e4c9d5fe7b6c9824011c4d97b57aaa97f24d41d82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A5XYM4CSJ4UYVV7S3SDJ7XBR2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Furong Huang, Guowei Xu, Huazhe Xu, Jiawei Guo, Ruijie Zheng, Tianying Ji, Yan Zeng, Yongyuan Liang, Yu Luo","submitted_at":"2024-02-22T13:22:06Z","abstract_excerpt":"The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14528","kind":"arxiv","version":5},"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/2402.14528/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":"2026-07-05T09:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KNmulROg0CiI0MrXuZss07baxHh/1teOaAkQ9X75CKV4/sGkDn50Fks6+0XiJnlmoOFEgwbGb7kPopkxwuzTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:57:25.856178Z"},"content_sha256":"aeaee66df0001927080a2c832c0310db893357abe5cbe6e9db856b5ee10cd40c","schema_version":"1.0","event_id":"sha256:aeaee66df0001927080a2c832c0310db893357abe5cbe6e9db856b5ee10cd40c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/bundle.json","state_url":"https://pith.science/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/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":"2026-07-21T04:57:25Z","links":{"resolver":"https://pith.science/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M","bundle":"https://pith.science/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/bundle.json","state":"https://pith.science/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5XYM4CSJ4UYVV7S3SDJ7XBR2M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A5XYM4CSJ4UYVV7S3SDJ7XBR2M","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":"cd4b19b476184bae4701dbfae483aa83779ba56a5c8f9b3ab076a5c3e8b25bb6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:22:06Z","title_canon_sha256":"d39d64654c292ca7d196f82488edd602943d91ab6a4fa8aa27c7244386e6d0da"},"schema_version":"1.0","source":{"id":"2402.14528","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14528","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14528v5","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14528","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"A5XYM4CSJ4UY","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"A5XYM4CSJ4UYVV7S","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"A5XYM4CS","created_at":"2026-07-05T09:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:aeaee66df0001927080a2c832c0310db893357abe5cbe6e9db856b5ee10cd40c","target":"graph","created_at":"2026-07-05T09:30:08Z","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/2402.14528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon ","authors_text":"Fuchun Sun, Furong Huang, Guowei Xu, Huazhe Xu, Jiawei Guo, Ruijie Zheng, Tianying Ji, Yan Zeng, Yongyuan Liang, Yu Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:22:06Z","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14528","kind":"arxiv","version":5},"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":"sha256:2c9cd6baaaf9612c8aa1db8e4c9d5fe7b6c9824011c4d97b57aaa97f24d41d82","target":"record","created_at":"2026-07-05T09:30:08Z","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":"cd4b19b476184bae4701dbfae483aa83779ba56a5c8f9b3ab076a5c3e8b25bb6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T13:22:06Z","title_canon_sha256":"d39d64654c292ca7d196f82488edd602943d91ab6a4fa8aa27c7244386e6d0da"},"schema_version":"1.0","source":{"id":"2402.14528","kind":"arxiv","version":5}},"canonical_sha256":"076f8670524f298ad7f2dc869fdc31d3164a995f28c06209592a7b30ec5f2ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"076f8670524f298ad7f2dc869fdc31d3164a995f28c06209592a7b30ec5f2ea3","first_computed_at":"2026-07-05T09:30:08.530545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:08.530545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VheWimG961ruJ7okoXfWOLB5Jd6iwcLq+jzIxQuLqWkgVImfbgvHYSRDLVauDCUjwtaGio0y172i4/vz1RA9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:08.531024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14528","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c9cd6baaaf9612c8aa1db8e4c9d5fe7b6c9824011c4d97b57aaa97f24d41d82","sha256:aeaee66df0001927080a2c832c0310db893357abe5cbe6e9db856b5ee10cd40c"],"state_sha256":"c8ef1b91564986a5d59623ebc64f11602644cedc68b7789ec1781ec959686ddb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLocQGp/9SHKXVT2rpDl1QUPi2kjO6+gAj1x0IrDiRpi9vmAzTIhB0LsnHl9+MCJYTRbBnhandG/VxJCGTUtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T04:57:25.858289Z","bundle_sha256":"8515a88fd3ce041b7acc0f2f08801d8bd2def6a61b9bccaa8f40fc6be02e6370"}}