{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JILSFLM6W6VSCKOVYXRFCGAUMV","short_pith_number":"pith:JILSFLM6","canonical_record":{"source":{"id":"2011.03383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-06T14:28:46Z","cross_cats_sorted":[],"title_canon_sha256":"533cbe4676d5298953fcb74c3b713d2c72d13fcd3d1b8707163cfe7f18b5a1f2","abstract_canon_sha256":"72aeec9fdd186b05d33689645e92849af79fcd6919fb614fb3f4a717cbbad18c"},"schema_version":"1.0"},"canonical_sha256":"4a1722ad9eb7ab2129d5c5e25118146546cab92acf1e89e13aa92124f559f510","source":{"kind":"arxiv","id":"2011.03383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03383","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03383v1","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03383","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"JILSFLM6W6VS","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"JILSFLM6W6VSCKOV","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"JILSFLM6","created_at":"2026-07-05T01:49:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JILSFLM6W6VSCKOVYXRFCGAUMV","target":"record","payload":{"canonical_record":{"source":{"id":"2011.03383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-06T14:28:46Z","cross_cats_sorted":[],"title_canon_sha256":"533cbe4676d5298953fcb74c3b713d2c72d13fcd3d1b8707163cfe7f18b5a1f2","abstract_canon_sha256":"72aeec9fdd186b05d33689645e92849af79fcd6919fb614fb3f4a717cbbad18c"},"schema_version":"1.0"},"canonical_sha256":"4a1722ad9eb7ab2129d5c5e25118146546cab92acf1e89e13aa92124f559f510","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:42.647157Z","signature_b64":"SWhRQeGfnvNozwYSl+yHsGm1XyLHwPXa/2i/tKdgPV6haPF4dQfmVBREOsYloyydPiGGOUj9xkBAzcva6XhuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a1722ad9eb7ab2129d5c5e25118146546cab92acf1e89e13aa92124f559f510","last_reissued_at":"2026-07-05T01:49:42.646601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:42.646601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.03383","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00lG9Dxr3LxBI5Ad1NJjVXUc45i9eta2m3PxRhd06Q2zPlkA6oDfWiNWgKQiGwN6POabffaoizNbwhEiu9wpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:20:35.389677Z"},"content_sha256":"5bd17609d84e418e48a7ffb85cefdb5fb92bc90e1a1883403bb2e98fcacc5dcc","schema_version":"1.0","event_id":"sha256:5bd17609d84e418e48a7ffb85cefdb5fb92bc90e1a1883403bb2e98fcacc5dcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JILSFLM6W6VSCKOVYXRFCGAUMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Skill Learning for Robust Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chao Yang, Di Guo, Fuchun Sun, Huaping Liu, Pingcheng Jian","submitted_at":"2020-11-06T14:28:46Z","abstract_excerpt":"Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are inevitable, thus the performance of the trained policy will dramatically drop. To improve the robustness of the policy, we introduce the adversarial training mechanism to the robotic manipulation tasks in this paper, and an adversarial skill learning algorithm based on soft actor-critic (SAC) is proposed for robust manipulation. Extensive experiments are conducted to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03383","kind":"arxiv","version":1},"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/2011.03383/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":"2026-07-05T01:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdY2+2j+qi9ap02wo3z0i/3eHpAYdLjbM5rAIvp0rnrnwmIR3pKDcQynuuMcMSlsxzdRRMsBIYMHK44gDLzPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:20:35.390051Z"},"content_sha256":"60eeae49b01145fabf48c0da410d1da558ebf9babfd4677e22626edda5fd9b44","schema_version":"1.0","event_id":"sha256:60eeae49b01145fabf48c0da410d1da558ebf9babfd4677e22626edda5fd9b44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/bundle.json","state_url":"https://pith.science/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/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":"2026-07-07T10:20:35Z","links":{"resolver":"https://pith.science/pith/JILSFLM6W6VSCKOVYXRFCGAUMV","bundle":"https://pith.science/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/bundle.json","state":"https://pith.science/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JILSFLM6W6VSCKOVYXRFCGAUMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JILSFLM6W6VSCKOVYXRFCGAUMV","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":"72aeec9fdd186b05d33689645e92849af79fcd6919fb614fb3f4a717cbbad18c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-06T14:28:46Z","title_canon_sha256":"533cbe4676d5298953fcb74c3b713d2c72d13fcd3d1b8707163cfe7f18b5a1f2"},"schema_version":"1.0","source":{"id":"2011.03383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03383","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03383v1","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03383","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"JILSFLM6W6VS","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"JILSFLM6W6VSCKOV","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"JILSFLM6","created_at":"2026-07-05T01:49:42Z"}],"graph_snapshots":[{"event_id":"sha256:60eeae49b01145fabf48c0da410d1da558ebf9babfd4677e22626edda5fd9b44","target":"graph","created_at":"2026-07-05T01:49:42Z","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/2011.03383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are inevitable, thus the performance of the trained policy will dramatically drop. To improve the robustness of the policy, we introduce the adversarial training mechanism to the robotic manipulation tasks in this paper, and an adversarial skill learning algorithm based on soft actor-critic (SAC) is proposed for robust manipulation. Extensive experiments are conducted to","authors_text":"Chao Yang, Di Guo, Fuchun Sun, Huaping Liu, Pingcheng Jian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-06T14:28:46Z","title":"Adversarial Skill Learning for Robust Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03383","kind":"arxiv","version":1},"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":"sha256:5bd17609d84e418e48a7ffb85cefdb5fb92bc90e1a1883403bb2e98fcacc5dcc","target":"record","created_at":"2026-07-05T01:49:42Z","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":"72aeec9fdd186b05d33689645e92849af79fcd6919fb614fb3f4a717cbbad18c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-06T14:28:46Z","title_canon_sha256":"533cbe4676d5298953fcb74c3b713d2c72d13fcd3d1b8707163cfe7f18b5a1f2"},"schema_version":"1.0","source":{"id":"2011.03383","kind":"arxiv","version":1}},"canonical_sha256":"4a1722ad9eb7ab2129d5c5e25118146546cab92acf1e89e13aa92124f559f510","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a1722ad9eb7ab2129d5c5e25118146546cab92acf1e89e13aa92124f559f510","first_computed_at":"2026-07-05T01:49:42.646601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:42.646601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWhRQeGfnvNozwYSl+yHsGm1XyLHwPXa/2i/tKdgPV6haPF4dQfmVBREOsYloyydPiGGOUj9xkBAzcva6XhuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:42.647157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bd17609d84e418e48a7ffb85cefdb5fb92bc90e1a1883403bb2e98fcacc5dcc","sha256:60eeae49b01145fabf48c0da410d1da558ebf9babfd4677e22626edda5fd9b44"],"state_sha256":"8478e9eb3a4ec627e02ae2b02a0d597313ff085257a2d32276e19ebe61dd3922"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxqiKT6KdMRTFAlrlbNJGimEFVpQMNoLRIf9Xmz1EI5f4/MmURPMpn07Dczu1pf0ktlhKJV2XsFpTIDpXoFvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:20:35.392104Z","bundle_sha256":"ec8df5111af141baf6cdab8dba9aab49cd48ae60a89fea8f66cc9303c0dcb45a"}}