{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MLLWSDENAV2K7VG4UZA2BSTB3B","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":"dd42eaf9a146daa014b6d1511bf1b82abdf1b1ff29d997f7cbc3cd42c2fcf7f9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-27T13:46:39Z","title_canon_sha256":"c24e38bef585f02c663e41d7b7999dbd12cbc294c5d3b816753fbb248d86128f"},"schema_version":"1.0","source":{"id":"2109.13050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.13050","created_at":"2026-07-05T04:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2109.13050v2","created_at":"2026-07-05T04:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13050","created_at":"2026-07-05T04:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"MLLWSDENAV2K","created_at":"2026-07-05T04:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"MLLWSDENAV2K7VG4","created_at":"2026-07-05T04:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"MLLWSDEN","created_at":"2026-07-05T04:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:5bd8a23b1cefa849c8d997c9dca6bc2ab4a0d64973cc83610072d0c1ba84c5c5","target":"graph","created_at":"2026-07-05T04:45:12Z","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/2109.13050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is a powerful mathematical framework that allows robots to learn complex skills by trial-and-error. Despite numerous successes in many applications, RL algorithms still require thousands of trials to converge to high-performing policies, can produce dangerous behaviors while learning, and the optimized policies (usually modeled as neural networks) give almost zero explanation when they fail to perform the task. For these reasons, the adoption of RL in industrial settings is not common. Behavior Trees (BTs), on the other hand, can provide a policy representation that","authors_text":"Faseeh Ahmad, Konstantinos Chatzilygeroudis, Luigi Nardi, Matthias Mayr, Volker Krueger","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-27T13:46:39Z","title":"Learning of Parameters in Behavior Trees for Movement Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13050","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":"sha256:852a8ccb22ecc9443cbafb872f23d9c6561836f52ef6bb5c36c2c4a232ff9ae7","target":"record","created_at":"2026-07-05T04:45:12Z","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":"dd42eaf9a146daa014b6d1511bf1b82abdf1b1ff29d997f7cbc3cd42c2fcf7f9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-27T13:46:39Z","title_canon_sha256":"c24e38bef585f02c663e41d7b7999dbd12cbc294c5d3b816753fbb248d86128f"},"schema_version":"1.0","source":{"id":"2109.13050","kind":"arxiv","version":2}},"canonical_sha256":"62d7690c8d0574afd4dca641a0ca61d8486b9e6ec281014f47f2e88106f64526","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62d7690c8d0574afd4dca641a0ca61d8486b9e6ec281014f47f2e88106f64526","first_computed_at":"2026-07-05T04:45:12.238997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:45:12.238997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nocFkzMx5AQ7TqTMUmvUvWzIAimneJ0enumQq4zuIOUXTUAX8HpYgPZpr8pxTCwhPzqXY0hXXecWEtCOiyRdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:45:12.239415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.13050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:852a8ccb22ecc9443cbafb872f23d9c6561836f52ef6bb5c36c2c4a232ff9ae7","sha256:5bd8a23b1cefa849c8d997c9dca6bc2ab4a0d64973cc83610072d0c1ba84c5c5"],"state_sha256":"aad8fba47324b3ba74fcf45387bc0c99ec556ddc808ee1e212326b3a33166847"}