{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EHX5XBACE2SEA65YGZ5JVK2VYE","short_pith_number":"pith:EHX5XBAC","canonical_record":{"source":{"id":"1812.05905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-13T04:44:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a0eead57a6af4d64627b4afcbc592d8bbe9ab2da6b86acda1d66508623f199d9","abstract_canon_sha256":"13776c61d94d6dd46b111808de2271c2224c2a49a203c3131a82fae8105043dc"},"schema_version":"1.0"},"canonical_sha256":"21efdb840226a4407bb8367a9aab55c11c13f9a29b6bc97d65e66c85df4be1d3","source":{"kind":"arxiv","id":"1812.05905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.05905","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"1812.05905v2","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05905","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"EHX5XBACE2SE","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"EHX5XBACE2SEA65Y","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"EHX5XBAC","created_at":"2026-07-05T00:04:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EHX5XBACE2SEA65YGZ5JVK2VYE","target":"record","payload":{"canonical_record":{"source":{"id":"1812.05905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-13T04:44:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a0eead57a6af4d64627b4afcbc592d8bbe9ab2da6b86acda1d66508623f199d9","abstract_canon_sha256":"13776c61d94d6dd46b111808de2271c2224c2a49a203c3131a82fae8105043dc"},"schema_version":"1.0"},"canonical_sha256":"21efdb840226a4407bb8367a9aab55c11c13f9a29b6bc97d65e66c85df4be1d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:26.765131Z","signature_b64":"G1XUQZ98PwN8VYDZYI/sYWEeNEpY9qTOSQQxgwsPQaSDGOBprL2QUrv51XxWl16m3TGhfQtX8KXGF0/KUWK1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21efdb840226a4407bb8367a9aab55c11c13f9a29b6bc97d65e66c85df4be1d3","last_reissued_at":"2026-07-05T00:04:26.764562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:26.764562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.05905","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":"2026-07-05T00:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9mjhzl6ZfMlwEcso18LwEBrD8X71dxf9K4ss8gRbR/Pl6mmkNrWb2LDB8k20LgAkT/ddg32lhMdxlxcT8a4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:19.547628Z"},"content_sha256":"5b8e9c39ee681a504c7e915f3d03dc2cd98397eb223bc11d86f34c09fdb0eb6b","schema_version":"1.0","event_id":"sha256:5b8e9c39ee681a504c7e915f3d03dc2cd98397eb223bc11d86f34c09fdb0eb6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EHX5XBACE2SEA65YGZ5JVK2VYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Actor-Critic Algorithms and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy.","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Aurick Zhou, George Tucker, Henry Zhu, Jie Tan, Kristian Hartikainen, Pieter Abbeel, Sehoon Ha, Sergey Levine, Tuomas Haarnoja, Vikash Kumar","submitted_at":"2018-12-13T04:44:29Z","abstract_excerpt":"Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the applicability of such methods to real-world domains. In this paper, we describe Soft Actor-Critic (SAC), our recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework. In this framework, the actor aims to simultaneously maximize expected retur"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With these improvements, SAC achieves state-of-the-art performance, outperforming prior on-policy and off-policy methods in sample-efficiency and asymptotic performance. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving similar performance across different random seeds.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The maximum entropy objective combined with the constrained temperature formulation will reliably produce the claimed stability and sample-efficiency gains without introducing new sensitivities or requiring task-specific adjustments beyond those described.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SAC extends maximum-entropy RL into a stable off-policy actor-critic method with constrained temperature tuning, outperforming prior algorithms in sample efficiency and consistency on locomotion and manipulation tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"26efed6b200535027f602698da034e20562262ba6b7dca9de42b70c9abb2d753"},"source":{"id":"1812.05905","kind":"arxiv","version":2},"verdict":{"id":"08f65c28-de8b-4ad1-91ba-21ffd893afcb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T14:28:07.440506Z","strongest_claim":"With these improvements, SAC achieves state-of-the-art performance, outperforming prior on-policy and off-policy methods in sample-efficiency and asymptotic performance. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving similar performance across different random seeds.","one_line_summary":"SAC extends maximum-entropy RL into a stable off-policy actor-critic method with constrained temperature tuning, outperforming prior algorithms in sample efficiency and consistency on locomotion and manipulation tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The maximum entropy objective combined with the constrained temperature formulation will reliably produce the claimed stability and sample-efficiency gains without introducing new sensitivities or requiring task-specific adjustments beyond those described.","pith_extraction_headline":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.05905/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":13,"sample":[{"doi":"","year":null,"title":"Maximum a Posteriori Policy Optimisation","work_id":"cb0e49f6-4417-4c5e-b4a8-567d7e9e76a7","ref_index":1,"cited_arxiv_id":"1806.06920","is_internal_anchor":false},{"doi":"","year":null,"title":"Brockman, G., Cheung, V ., Pettersson, L., Schneider, J., Schulman, J., Tang, J., and Zaremba, W. OpenAI gym. arXiv preprint arXiv:1606.01540,","work_id":"6af98f3f-f074-41ae-a689-7dd7b4b8efde","ref_index":2,"cited_arxiv_id":"1606.01540","is_internal_anchor":true},{"doi":"","year":null,"title":"Addressing Function Approximation Error in Actor-Critic Methods","work_id":"129bee39-1830-4ff5-a7c3-f8ecae60f370","ref_index":3,"cited_arxiv_id":"1802.09477","is_internal_anchor":false},{"doi":"","year":null,"title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","work_id":"2b8d4fd3-3479-478a-bc44-f6d493e0616c","ref_index":4,"cited_arxiv_id":"1704.04651","is_internal_anchor":false},{"doi":"","year":null,"title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","work_id":"3570547f-d4c5-4808-a945-f27a73bb7d90","ref_index":5,"cited_arxiv_id":"1611.02247","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"0adc4b01225bce4f0d15664dce89cd286c589b6fd9bba65ef0c1fd7b744c9b72","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d7687933b3c72b1d19c26a4bec58cdba8276062556b23ccefcad7fe06d7c018d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"08f65c28-de8b-4ad1-91ba-21ffd893afcb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkgRx0bwB1NVc7vvc8VWttRKEAfmYv5r0GT6SsXjmIbMpxwHqMq4bzPTVo9JunJ1GDOXpethIYa9454emB8+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:11:19.548174Z"},"content_sha256":"fc0ae6b110b8f59c5026240d13bac7df18011a5b70b35627fd4351f56bd0032b","schema_version":"1.0","event_id":"sha256:fc0ae6b110b8f59c5026240d13bac7df18011a5b70b35627fd4351f56bd0032b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/bundle.json","state_url":"https://pith.science/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/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":"2026-08-06T17:11:19Z","links":{"resolver":"https://pith.science/pith/EHX5XBACE2SEA65YGZ5JVK2VYE","bundle":"https://pith.science/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/bundle.json","state":"https://pith.science/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHX5XBACE2SEA65YGZ5JVK2VYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EHX5XBACE2SEA65YGZ5JVK2VYE","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":"13776c61d94d6dd46b111808de2271c2224c2a49a203c3131a82fae8105043dc","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-13T04:44:29Z","title_canon_sha256":"a0eead57a6af4d64627b4afcbc592d8bbe9ab2da6b86acda1d66508623f199d9"},"schema_version":"1.0","source":{"id":"1812.05905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.05905","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"1812.05905v2","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05905","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"EHX5XBACE2SE","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"EHX5XBACE2SEA65Y","created_at":"2026-07-05T00:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"EHX5XBAC","created_at":"2026-07-05T00:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:fc0ae6b110b8f59c5026240d13bac7df18011a5b70b35627fd4351f56bd0032b","target":"graph","created_at":"2026-07-05T00:04:26Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With these improvements, SAC achieves state-of-the-art performance, outperforming prior on-policy and off-policy methods in sample-efficiency and asymptotic performance. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving similar performance across different random seeds."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The maximum entropy objective combined with the constrained temperature formulation will reliably produce the claimed stability and sample-efficiency gains without introducing new sensitivities or requiring task-specific adjustments beyond those described."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SAC extends maximum-entropy RL into a stable off-policy actor-critic method with constrained temperature tuning, outperforming prior algorithms in sample efficiency and consistency on locomotion and manipulation tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy."}],"snapshot_sha256":"26efed6b200535027f602698da034e20562262ba6b7dca9de42b70c9abb2d753"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d7687933b3c72b1d19c26a4bec58cdba8276062556b23ccefcad7fe06d7c018d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1812.05905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the applicability of such methods to real-world domains. In this paper, we describe Soft Actor-Critic (SAC), our recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework. In this framework, the actor aims to simultaneously maximize expected retur","authors_text":"Abhishek Gupta, Aurick Zhou, George Tucker, Henry Zhu, Jie Tan, Kristian Hartikainen, Pieter Abbeel, Sehoon Ha, Sergey Levine, Tuomas Haarnoja, Vikash Kumar","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-13T04:44:29Z","title":"Soft Actor-Critic Algorithms and Applications"},"references":{"count":13,"internal_anchors":4,"resolved_work":13,"sample":[{"cited_arxiv_id":"1806.06920","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Maximum a Posteriori Policy Optimisation","work_id":"cb0e49f6-4417-4c5e-b4a8-567d7e9e76a7","year":null},{"cited_arxiv_id":"1606.01540","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Brockman, G., Cheung, V ., Pettersson, L., Schneider, J., Schulman, J., Tang, J., and Zaremba, W. OpenAI gym. arXiv preprint arXiv:1606.01540,","work_id":"6af98f3f-f074-41ae-a689-7dd7b4b8efde","year":null},{"cited_arxiv_id":"1802.09477","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Addressing Function Approximation Error in Actor-Critic Methods","work_id":"129bee39-1830-4ff5-a7c3-f8ecae60f370","year":null},{"cited_arxiv_id":"1704.04651","doi":"","is_internal_anchor":false,"ref_index":4,"title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","work_id":"2b8d4fd3-3479-478a-bc44-f6d493e0616c","year":null},{"cited_arxiv_id":"1611.02247","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","work_id":"3570547f-d4c5-4808-a945-f27a73bb7d90","year":null}],"snapshot_sha256":"0adc4b01225bce4f0d15664dce89cd286c589b6fd9bba65ef0c1fd7b744c9b72"},"source":{"id":"1812.05905","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T14:28:07.440506Z","id":"08f65c28-de8b-4ad1-91ba-21ffd893afcb","model_set":{"reader":"grok-4.3"},"one_line_summary":"SAC extends maximum-entropy RL into a stable off-policy actor-critic method with constrained temperature tuning, outperforming prior algorithms in sample efficiency and consistency on locomotion and manipulation tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Soft Actor-Critic achieves state-of-the-art sample efficiency and stability in reinforcement learning by maximizing both task reward and policy entropy.","strongest_claim":"With these improvements, SAC achieves state-of-the-art performance, outperforming prior on-policy and off-policy methods in sample-efficiency and asymptotic performance. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving similar performance across different random seeds.","weakest_assumption":"The maximum entropy objective combined with the constrained temperature formulation will reliably produce the claimed stability and sample-efficiency gains without introducing new sensitivities or requiring task-specific adjustments beyond those described."}},"verdict_id":"08f65c28-de8b-4ad1-91ba-21ffd893afcb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b8e9c39ee681a504c7e915f3d03dc2cd98397eb223bc11d86f34c09fdb0eb6b","target":"record","created_at":"2026-07-05T00:04:26Z","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":"13776c61d94d6dd46b111808de2271c2224c2a49a203c3131a82fae8105043dc","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-13T04:44:29Z","title_canon_sha256":"a0eead57a6af4d64627b4afcbc592d8bbe9ab2da6b86acda1d66508623f199d9"},"schema_version":"1.0","source":{"id":"1812.05905","kind":"arxiv","version":2}},"canonical_sha256":"21efdb840226a4407bb8367a9aab55c11c13f9a29b6bc97d65e66c85df4be1d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21efdb840226a4407bb8367a9aab55c11c13f9a29b6bc97d65e66c85df4be1d3","first_computed_at":"2026-07-05T00:04:26.764562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:26.764562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G1XUQZ98PwN8VYDZYI/sYWEeNEpY9qTOSQQxgwsPQaSDGOBprL2QUrv51XxWl16m3TGhfQtX8KXGF0/KUWK1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:26.765131Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.05905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b8e9c39ee681a504c7e915f3d03dc2cd98397eb223bc11d86f34c09fdb0eb6b","sha256:fc0ae6b110b8f59c5026240d13bac7df18011a5b70b35627fd4351f56bd0032b"],"state_sha256":"44cdaf1c1ca8587c906929ab5dccfc28b734ba60eac4356cc661b9cf4fdee314"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewEWAORvZnm8v9EvcQXYuytFPFXw3tZW4JZbHJC8Qs/0vdlzptOg7U77uDu6wHEew2ehVJDZb1Wf27C3410GBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:11:19.551645Z","bundle_sha256":"02023a08e5d9ead04e5750d1872839aca19d137c01d05dab0fbf688cc068fc9b"}}