{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CURLCISNPPWUOQ7EAU6UMVT7DL","short_pith_number":"pith:CURLCISN","canonical_record":{"source":{"id":"2304.13653","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-26T16:25:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"731814e8a78228f65b05517c734317f569ef00d0307440299b86c3be2cd2e0a4","abstract_canon_sha256":"9f1203196bdb454f8c7c428638261a22ae67b5cfebd22bf5071e260808745d32"},"schema_version":"1.0"},"canonical_sha256":"1522b1224d7bed4743e4053d46567f1aef2769fc54d405e4a40a1d8a581ac303","source":{"kind":"arxiv","id":"2304.13653","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13653","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13653v2","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13653","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"CURLCISNPPWU","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"CURLCISNPPWUOQ7E","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"CURLCISN","created_at":"2026-07-05T08:06:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CURLCISNPPWUOQ7EAU6UMVT7DL","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13653","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-26T16:25:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"731814e8a78228f65b05517c734317f569ef00d0307440299b86c3be2cd2e0a4","abstract_canon_sha256":"9f1203196bdb454f8c7c428638261a22ae67b5cfebd22bf5071e260808745d32"},"schema_version":"1.0"},"canonical_sha256":"1522b1224d7bed4743e4053d46567f1aef2769fc54d405e4a40a1d8a581ac303","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:40.778457Z","signature_b64":"OGUk6+XsXM/I8lY2W5RbzVxk4lj8QvszTk+7JuMoyErJ4yRh1E6t0wnPczTcvO3QGwOmR4oL7bmQB0CTxh+tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1522b1224d7bed4743e4053d46567f1aef2769fc54d405e4a40a1d8a581ac303","last_reissued_at":"2026-07-05T08:06:40.777975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:40.777975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13653","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":"2026-07-05T08:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4kDvTLcffx1ktCKVRNsY2j7VpGYFc5Wd9+0ExcSxRNbw4Z7OA4YXSc48AC8jj3ENWzFLnAUKQnXYzadgXPWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:23:18.488344Z"},"content_sha256":"57248e2e905e6c142dbc1eb395a6c1a0009530b41c99321f9ef25972d3695910","schema_version":"1.0","event_id":"sha256:57248e2e905e6c142dbc1eb395a6c1a0009530b41c99321f9ef25972d3695910"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CURLCISNPPWUOQ7EAU6UMVT7DL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Huber, Arunkumar Byravan, Ben Moran, Charles Game, Dhruva Tirumala, Federico Casarini, Fereshteh Sadeghi, Francesco Nori, Guy Lever, Jan Humplik, Kristian Hartikainen, Kushal Patel, Leonard Hasenclever, Markus Wulfmeier, Marlon Gwira, Michael Bloesch, Nathan Batchelor, Neil Sreendra, Nicolas Heess, Nicole Hurley, Noah Y. Siegel, Raia Hadsell, Roland Hafner, Sandy H. Huang, Saran Tunyasuvunakool, Stefano Saliceti, Tuomas Haarnoja, Yuval Tassa","submitted_at":"2023-04-26T16:25:54Z","abstract_excerpt":"We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. The resulting agent exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and it transitions between them in a smooth, stable, and efficient manner. The agent's locomotion and tact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13653","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/2304.13653/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":"2026-07-05T08:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkPjaNiaRHFXsNx4a9WTylcSpafTyUV7FeQ+kBRnJj2eIB3ncdp/dMlFCQjsm6DP8RLOxUL50kXoGYoRKuDpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:23:18.488733Z"},"content_sha256":"0a22653d0a729108b99814331c5706f595a8b76990acae28aecf7300ff02fabf","schema_version":"1.0","event_id":"sha256:0a22653d0a729108b99814331c5706f595a8b76990acae28aecf7300ff02fabf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/bundle.json","state_url":"https://pith.science/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/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":"2026-07-07T03:23:18Z","links":{"resolver":"https://pith.science/pith/CURLCISNPPWUOQ7EAU6UMVT7DL","bundle":"https://pith.science/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/bundle.json","state":"https://pith.science/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CURLCISNPPWUOQ7EAU6UMVT7DL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CURLCISNPPWUOQ7EAU6UMVT7DL","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":"9f1203196bdb454f8c7c428638261a22ae67b5cfebd22bf5071e260808745d32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-26T16:25:54Z","title_canon_sha256":"731814e8a78228f65b05517c734317f569ef00d0307440299b86c3be2cd2e0a4"},"schema_version":"1.0","source":{"id":"2304.13653","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13653","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13653v2","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13653","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"CURLCISNPPWU","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"CURLCISNPPWUOQ7E","created_at":"2026-07-05T08:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"CURLCISN","created_at":"2026-07-05T08:06:40Z"}],"graph_snapshots":[{"event_id":"sha256:0a22653d0a729108b99814331c5706f595a8b76990acae28aecf7300ff02fabf","target":"graph","created_at":"2026-07-05T08:06:40Z","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/2304.13653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. The resulting agent exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and it transitions between them in a smooth, stable, and efficient manner. The agent's locomotion and tact","authors_text":"Andrea Huber, Arunkumar Byravan, Ben Moran, Charles Game, Dhruva Tirumala, Federico Casarini, Fereshteh Sadeghi, Francesco Nori, Guy Lever, Jan Humplik, Kristian Hartikainen, Kushal Patel, Leonard Hasenclever, Markus Wulfmeier, Marlon Gwira, Michael Bloesch, Nathan Batchelor, Neil Sreendra, Nicolas Heess, Nicole Hurley, Noah Y. Siegel, Raia Hadsell, Roland Hafner, Sandy H. Huang, Saran Tunyasuvunakool, Stefano Saliceti, Tuomas Haarnoja, Yuval Tassa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-26T16:25:54Z","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13653","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":"sha256:57248e2e905e6c142dbc1eb395a6c1a0009530b41c99321f9ef25972d3695910","target":"record","created_at":"2026-07-05T08:06:40Z","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":"9f1203196bdb454f8c7c428638261a22ae67b5cfebd22bf5071e260808745d32","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-26T16:25:54Z","title_canon_sha256":"731814e8a78228f65b05517c734317f569ef00d0307440299b86c3be2cd2e0a4"},"schema_version":"1.0","source":{"id":"2304.13653","kind":"arxiv","version":2}},"canonical_sha256":"1522b1224d7bed4743e4053d46567f1aef2769fc54d405e4a40a1d8a581ac303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1522b1224d7bed4743e4053d46567f1aef2769fc54d405e4a40a1d8a581ac303","first_computed_at":"2026-07-05T08:06:40.777975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:40.777975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGUk6+XsXM/I8lY2W5RbzVxk4lj8QvszTk+7JuMoyErJ4yRh1E6t0wnPczTcvO3QGwOmR4oL7bmQB0CTxh+tAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:40.778457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13653","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57248e2e905e6c142dbc1eb395a6c1a0009530b41c99321f9ef25972d3695910","sha256:0a22653d0a729108b99814331c5706f595a8b76990acae28aecf7300ff02fabf"],"state_sha256":"a74633bf4e452fb08854412c85d8c0eb0be8a838223eff3bf9163cd5880b236f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OjHdv1C/NMBH2iX1zvyr0mVpJ3F3GLC2kqdzGhvSYkc6Q3SKXdXoOWMlbd0InubTfWgujddQl2xhJZA6WuMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:23:18.490747Z","bundle_sha256":"fe7add8f76bf8130321e7a4c4456fdfbf6a14fe48421ce956368b5c542597557"}}