{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U54A2USE5AAUYLTYEDF7RQIAQH","short_pith_number":"pith:U54A2USE","canonical_record":{"source":{"id":"2304.08743","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7","abstract_canon_sha256":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe"},"schema_version":"1.0"},"canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","source":{"kind":"arxiv","id":"2304.08743","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08743v2","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"U54A2USE5AAU","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"U54A2USE5AAUYLTY","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"U54A2USE","created_at":"2026-07-05T06:26:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U54A2USE5AAUYLTYEDF7RQIAQH","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08743","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7","abstract_canon_sha256":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe"},"schema_version":"1.0"},"canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:01.802370Z","signature_b64":"dLS1Hn/fvHPHGmqkQ0nCZMYB13+UcITCVeJSPT+Fj21Pm8aEJjg4FNuJ+ENTTf7WiaSKx+cGWSXlzZJLDsSdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","last_reissued_at":"2026-07-05T06:26:01.801935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:01.801935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08743","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":"2026-07-05T06:26:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9lnaqxMoOFFkBchB0kZdzsDwdXTxW3rSee8OowkLdWnprIYIMS3Kyn24HaG/2qSQrzmTCjGid86qLAqRQ7qTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:35:25.725235Z"},"content_sha256":"0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe","schema_version":"1.0","event_id":"sha256:0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U54A2USE5AAUYLTYEDF7RQIAQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Kazumi Kasaura, Kenta Hoshino, Ryo Yonetani, Shuwa Miura, Tadashi Kozuno, Yohei Hosoe","submitted_at":"2023-04-18T05:45:09Z","abstract_excerpt":"This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08743","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/2304.08743/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":"2026-07-05T06:26:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pK4PYV2O1xvJFCsHSnSGYKn3zUHpknCQHbr3qEN6U1dEu7Ltpf52lGvEHrPAwSlp8fvsXJkt/3ZhpZ0DhMkeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:35:25.725761Z"},"content_sha256":"8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4","schema_version":"1.0","event_id":"sha256:8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U54A2USE5AAUYLTYEDF7RQIAQH/bundle.json","state_url":"https://pith.science/pith/U54A2USE5AAUYLTYEDF7RQIAQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U54A2USE5AAUYLTYEDF7RQIAQH/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":"2026-08-05T16:35:25Z","links":{"resolver":"https://pith.science/pith/U54A2USE5AAUYLTYEDF7RQIAQH","bundle":"https://pith.science/pith/U54A2USE5AAUYLTYEDF7RQIAQH/bundle.json","state":"https://pith.science/pith/U54A2USE5AAUYLTYEDF7RQIAQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U54A2USE5AAUYLTYEDF7RQIAQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U54A2USE5AAUYLTYEDF7RQIAQH","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":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7"},"schema_version":"1.0","source":{"id":"2304.08743","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08743v2","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"U54A2USE5AAU","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"U54A2USE5AAUYLTY","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"U54A2USE","created_at":"2026-07-05T06:26:01Z"}],"graph_snapshots":[{"event_id":"sha256:8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4","target":"graph","created_at":"2026-07-05T06:26:01Z","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/2304.08743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a s","authors_text":"Kazumi Kasaura, Kenta Hoshino, Ryo Yonetani, Shuwa Miura, Tadashi Kozuno, Yohei Hosoe","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08743","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":"sha256:0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe","target":"record","created_at":"2026-07-05T06:26:01Z","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":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7"},"schema_version":"1.0","source":{"id":"2304.08743","kind":"arxiv","version":2}},"canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","first_computed_at":"2026-07-05T06:26:01.801935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:01.801935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dLS1Hn/fvHPHGmqkQ0nCZMYB13+UcITCVeJSPT+Fj21Pm8aEJjg4FNuJ+ENTTf7WiaSKx+cGWSXlzZJLDsSdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:01.802370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08743","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe","sha256:8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4"],"state_sha256":"a86567f82e7eff919d52dd226f245032962e30e8735b705e9ee9958dc75ac6d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7PFNgqj5l4aLKoIcs2PN+O3VS8PUwXoemVcB0Axe/7fASe8GKZKBR/2I1VKA/hoW4L5Ni43rD3ykjFR7MRmCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:35:25.732697Z","bundle_sha256":"dd6ef7d219705c447a658de5090319641e8f238e4a247a73d3464ce832d86150"}}