{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SD7WNCF56IN2CB2TKGETLTC7FI","short_pith_number":"pith:SD7WNCF5","canonical_record":{"source":{"id":"2501.09080","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T19:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63034f36de7feb19850d800e2ddc058451bcaa153d5ad4bf9ac7131ef5263438","abstract_canon_sha256":"f0c4027534a4d9ddc37368252e4becd5c190bb137784e46769ee2c06093c2509"},"schema_version":"1.0"},"canonical_sha256":"90ff6688bdf21ba10753518935cc5f2a21015338db8c4e19e905da77e6723bc6","source":{"kind":"arxiv","id":"2501.09080","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09080","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09080v2","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09080","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"SD7WNCF56IN2","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"SD7WNCF56IN2CB2T","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"SD7WNCF5","created_at":"2026-07-05T11:48:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SD7WNCF56IN2CB2TKGETLTC7FI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09080","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T19:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63034f36de7feb19850d800e2ddc058451bcaa153d5ad4bf9ac7131ef5263438","abstract_canon_sha256":"f0c4027534a4d9ddc37368252e4becd5c190bb137784e46769ee2c06093c2509"},"schema_version":"1.0"},"canonical_sha256":"90ff6688bdf21ba10753518935cc5f2a21015338db8c4e19e905da77e6723bc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:47.164454Z","signature_b64":"utFsVfDodk9N0D7h+SI98zvQhVPMQg0vxkK5fzVeOhNih1QBwhMj+J0yR5qVKNepWS74hkZFNmDPDCQ0ixyHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ff6688bdf21ba10753518935cc5f2a21015338db8c4e19e905da77e6723bc6","last_reissued_at":"2026-07-05T11:48:47.163983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:47.163983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09080","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":"2026-07-05T11:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z03JAYCcJB+KcgWSOlJDGmw3er1CphbWvVgIKrqO/oWCMlq9Bp4xrOPWFxhwECCaZ310s8EYiJZOWg+cs6ajDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:48:48.701672Z"},"content_sha256":"f570416335a4ab6ee8f865b18d511f51a3f140a01c0574b91a56a0430b56760d","schema_version":"1.0","event_id":"sha256:f570416335a4ab6ee8f865b18d511f51a3f140a01c0574b91a56a0430b56760d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SD7WNCF56IN2CB2TKGETLTC7FI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Average-Reward Soft Actor-Critic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","submitted_at":"2025-01-15T19:00:46Z","abstract_excerpt":"The average-reward formulation of reinforcement learning (RL) has drawn increased interest in recent years for its ability to solve temporally-extended problems without relying on discounting. Meanwhile, in the discounted setting, algorithms with entropy regularization have been developed, leading to improvements over deterministic methods. Despite the distinct benefits of these approaches, deep RL algorithms for the entropy-regularized average-reward objective have not been developed. While policy-gradient based approaches have recently been presented for the average-reward literature, the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09080","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/2501.09080/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":"2026-07-05T11:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEGfR6NIdc3Hch/XSK9iu4CyQN7SP2iiP8fbPYtpNnUj7T3QUZKrx0hM6N1/qLtpWChJiBRR11TW5Z0oGUeFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:48:48.702162Z"},"content_sha256":"37bcf73905e1063018c9643ff2182402a4a2e5255069328c6487f2663266cc6d","schema_version":"1.0","event_id":"sha256:37bcf73905e1063018c9643ff2182402a4a2e5255069328c6487f2663266cc6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SD7WNCF56IN2CB2TKGETLTC7FI/bundle.json","state_url":"https://pith.science/pith/SD7WNCF56IN2CB2TKGETLTC7FI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SD7WNCF56IN2CB2TKGETLTC7FI/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":"2026-08-15T23:48:48Z","links":{"resolver":"https://pith.science/pith/SD7WNCF56IN2CB2TKGETLTC7FI","bundle":"https://pith.science/pith/SD7WNCF56IN2CB2TKGETLTC7FI/bundle.json","state":"https://pith.science/pith/SD7WNCF56IN2CB2TKGETLTC7FI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SD7WNCF56IN2CB2TKGETLTC7FI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SD7WNCF56IN2CB2TKGETLTC7FI","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":"f0c4027534a4d9ddc37368252e4becd5c190bb137784e46769ee2c06093c2509","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T19:00:46Z","title_canon_sha256":"63034f36de7feb19850d800e2ddc058451bcaa153d5ad4bf9ac7131ef5263438"},"schema_version":"1.0","source":{"id":"2501.09080","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09080","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09080v2","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09080","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"SD7WNCF56IN2","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"SD7WNCF56IN2CB2T","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"SD7WNCF5","created_at":"2026-07-05T11:48:47Z"}],"graph_snapshots":[{"event_id":"sha256:37bcf73905e1063018c9643ff2182402a4a2e5255069328c6487f2663266cc6d","target":"graph","created_at":"2026-07-05T11:48:47Z","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/2501.09080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The average-reward formulation of reinforcement learning (RL) has drawn increased interest in recent years for its ability to solve temporally-extended problems without relying on discounting. Meanwhile, in the discounted setting, algorithms with entropy regularization have been developed, leading to improvements over deterministic methods. Despite the distinct benefits of these approaches, deep RL algorithms for the entropy-regularized average-reward objective have not been developed. While policy-gradient based approaches have recently been presented for the average-reward literature, the co","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T19:00:46Z","title":"Average-Reward Soft Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09080","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:f570416335a4ab6ee8f865b18d511f51a3f140a01c0574b91a56a0430b56760d","target":"record","created_at":"2026-07-05T11:48:47Z","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":"f0c4027534a4d9ddc37368252e4becd5c190bb137784e46769ee2c06093c2509","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T19:00:46Z","title_canon_sha256":"63034f36de7feb19850d800e2ddc058451bcaa153d5ad4bf9ac7131ef5263438"},"schema_version":"1.0","source":{"id":"2501.09080","kind":"arxiv","version":2}},"canonical_sha256":"90ff6688bdf21ba10753518935cc5f2a21015338db8c4e19e905da77e6723bc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90ff6688bdf21ba10753518935cc5f2a21015338db8c4e19e905da77e6723bc6","first_computed_at":"2026-07-05T11:48:47.163983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:47.163983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"utFsVfDodk9N0D7h+SI98zvQhVPMQg0vxkK5fzVeOhNih1QBwhMj+J0yR5qVKNepWS74hkZFNmDPDCQ0ixyHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:47.164454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09080","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f570416335a4ab6ee8f865b18d511f51a3f140a01c0574b91a56a0430b56760d","sha256:37bcf73905e1063018c9643ff2182402a4a2e5255069328c6487f2663266cc6d"],"state_sha256":"2992589c113b303fa5953c18a538f17b281086b51d3cb9f906945451f419c438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rGhhStQ33XGJ3gJpooe7Rxv40zcZYnDi+6EYlgPD9kNN0Rdn8ZE02pZH+bEUf3MxRnVA9zfg/WIZFWwjjNN7AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:48:48.707216Z","bundle_sha256":"fd54044b0ad5cb084fcf2d0b2933f5458b8a4f0cd5e3d5a42eff6a20344cb5c9"}}