{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6JKDN33FIIOV5QLUQPHPJJ6WYR","short_pith_number":"pith:6JKDN33F","canonical_record":{"source":{"id":"2411.19732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091","abstract_canon_sha256":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a"},"schema_version":"1.0"},"canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","source":{"kind":"arxiv","id":"2411.19732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19732v1","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_12","alias_value":"6JKDN33FIIOV","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_16","alias_value":"6JKDN33FIIOV5QLU","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_8","alias_value":"6JKDN33F","created_at":"2026-07-05T09:42:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6JKDN33FIIOV5QLUQPHPJJ6WYR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091","abstract_canon_sha256":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a"},"schema_version":"1.0"},"canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:07.451017Z","signature_b64":"bNxL9PnW3PeSulWL673XiSQk3xXE4NiliH8wslt3q74dnCxOwpUjubrsbIuQ+wbJJ+9aoARu9QUOR6MrMaPbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","last_reissued_at":"2026-07-05T09:42:07.450385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:07.450385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19732","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":"2026-07-05T09:42:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLAwQBW5ZCf7zvH+riIAjANGYhczqkChGDCs+UV7EFsbB5mm0Fd1ZecaGn9DOmZRaGdOamarzAYiM2/AXs9EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:15.465178Z"},"content_sha256":"e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba","schema_version":"1.0","event_id":"sha256:e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6JKDN33FIIOV5QLUQPHPJJ6WYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Eduardo Gonzalez-Sanchez, Gabriele Fadini, Severin Bochem, Yves Bicker","submitted_at":"2024-11-29T14:25:54Z","abstract_excerpt":"Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact gradients, they can be unstable in contact-rich environments and may lead to poor generalization. This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms. Our simulation results demonstrate that our method, tested on contact-rich environments, significantly enhances policy robustness "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19732","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/2411.19732/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":"2026-07-05T09:42:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMeke1nm8IehhdYW28dGVo/TFp1tdzPHstjdSveYdSIigJvztmDp+ITa1Ktl7AITosgUoBfwVjMbFCAn+JowAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:15.465554Z"},"content_sha256":"018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4","schema_version":"1.0","event_id":"sha256:018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/bundle.json","state_url":"https://pith.science/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/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":"2026-08-07T23:29:15Z","links":{"resolver":"https://pith.science/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR","bundle":"https://pith.science/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/bundle.json","state":"https://pith.science/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JKDN33FIIOV5QLUQPHPJJ6WYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6JKDN33FIIOV5QLUQPHPJJ6WYR","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":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091"},"schema_version":"1.0","source":{"id":"2411.19732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19732v1","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_12","alias_value":"6JKDN33FIIOV","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_16","alias_value":"6JKDN33FIIOV5QLU","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_8","alias_value":"6JKDN33F","created_at":"2026-07-05T09:42:07Z"}],"graph_snapshots":[{"event_id":"sha256:018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4","target":"graph","created_at":"2026-07-05T09:42:07Z","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/2411.19732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact gradients, they can be unstable in contact-rich environments and may lead to poor generalization. This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms. Our simulation results demonstrate that our method, tested on contact-rich environments, significantly enhances policy robustness ","authors_text":"Eduardo Gonzalez-Sanchez, Gabriele Fadini, Severin Bochem, Yves Bicker","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title":"Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19732","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:e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba","target":"record","created_at":"2026-07-05T09:42:07Z","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":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091"},"schema_version":"1.0","source":{"id":"2411.19732","kind":"arxiv","version":1}},"canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","first_computed_at":"2026-07-05T09:42:07.450385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:07.450385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bNxL9PnW3PeSulWL673XiSQk3xXE4NiliH8wslt3q74dnCxOwpUjubrsbIuQ+wbJJ+9aoARu9QUOR6MrMaPbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:07.451017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba","sha256:018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4"],"state_sha256":"32eca2473e2416b53c2c11dd83cf4fcd45dbd4491026200417f3be3652e5a7d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLLCjz33kvDFGyO00F9aum0+I5W3UIukn5RtSPdRRP7ZnENRJq/auKjHum3pqlSgq0o3lGyvKlnDIKGCd4AJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:29:15.468588Z","bundle_sha256":"ed34359c1a245609fe3cf45a635c87c9c33ccb4a2bac18c3d0b0ee3b7c0081f2"}}