{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BN4P6QA5PG3YB5GI6OR66C2AQK","short_pith_number":"pith:BN4P6QA5","canonical_record":{"source":{"id":"2604.09487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T16:52:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d3db323fa786e629f2692740a55f79c5dab4845ccc1c51f07af94aae6634ae3","abstract_canon_sha256":"383b8d823224d140c3ec76d7ee142a4e5a04776252f74690b5d11f705b20ca02"},"schema_version":"1.0"},"canonical_sha256":"0b78ff401d79b780f4c8f3a3ef0b4082984da59798f69217f9dc503fafcc691c","source":{"kind":"arxiv","id":"2604.09487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09487","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09487v2","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09487","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"BN4P6QA5PG3Y","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"BN4P6QA5PG3YB5GI","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"BN4P6QA5","created_at":"2026-06-02T02:04:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BN4P6QA5PG3YB5GI6OR66C2AQK","target":"record","payload":{"canonical_record":{"source":{"id":"2604.09487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T16:52:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d3db323fa786e629f2692740a55f79c5dab4845ccc1c51f07af94aae6634ae3","abstract_canon_sha256":"383b8d823224d140c3ec76d7ee142a4e5a04776252f74690b5d11f705b20ca02"},"schema_version":"1.0"},"canonical_sha256":"0b78ff401d79b780f4c8f3a3ef0b4082984da59798f69217f9dc503fafcc691c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:17.330020Z","signature_b64":"BXl7ynIiogWK404UYKkxdwhpRyzv/qqcbCBtUW6GLH0HZKYpSw8/K+w9tUEeoeY4J9cT8FNHxLmmgY8JhvQlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b78ff401d79b780f4c8f3a3ef0b4082984da59798f69217f9dc503fafcc691c","last_reissued_at":"2026-06-02T02:04:17.329467Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:17.329467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.09487","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":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnFAcchMuguWTnYq2Dbi1VDbN9VNPn4JBOf3/PzD9VOSABQXid4/IsbEOlAIF0uod4j56fVDNlVFJ4CVhjSRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:23:48.430486Z"},"content_sha256":"bc16813c9dfbbe846ccac04eef0c4bfc0b9af5adfe126ddbac6e151963e030e7","schema_version":"1.0","event_id":"sha256:bc16813c9dfbbe846ccac04eef0c4bfc0b9af5adfe126ddbac6e151963e030e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BN4P6QA5PG3YB5GI6OR66C2AQK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot.","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bernhard Sch\\\"olkopf, Dieter B\\\"uchler, Ingmar Posner, Jan Schneider, Le Chen, Mridul Mahajan, Simon Guist","submitted_at":"2026-04-10T16:52:54Z","abstract_excerpt":"Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition. Still, these systems are rarely used in practice due to inherent nonlinearities, friction, and hysteresis, which complicate modeling and control. So far, these challenges have hindered policy transfer from simulation to real systems. To bridge this gap, we propose a sim-to-real pipeline that learns a neural network model of this complex actuation and leverages established rigid body simulation for the arm dynamics and interactions with the environment. Our method, ca"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using GeAN on PAMY2, a tendon-driven robot powered by pneumatic artificial muscles, we successfully deploy precise goal-reaching and dynamic ball-in-a-cup policies trained entirely in simulation. To the best of our knowledge, this result constitutes the first successful sim-to-real transfer for a four-degrees-of-freedom muscle-actuated robot arm.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a neural network trained solely on joint position trajectories can capture the nonlinear actuator dynamics (friction, hysteresis) with sufficient accuracy to enable zero-shot policy transfer from the hybrid simulation to the physical robot without torque sensing or additional adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GeAN learns actuator dynamics from position trajectories to enable successful sim-to-real transfer of goal-reaching and ball-in-a-cup policies on a 4-DoF pneumatic muscle-actuated robot, reported as the first such transfer for this system type.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"22f9cd768e05f41bfb3126dc2e45d146c608acdf1e386cdb8af5f20e1d6572b8"},"source":{"id":"2604.09487","kind":"arxiv","version":2},"verdict":{"id":"f0908cb4-f915-4f69-9a00-e2e79c636ebb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:49:19.078419Z","strongest_claim":"Using GeAN on PAMY2, a tendon-driven robot powered by pneumatic artificial muscles, we successfully deploy precise goal-reaching and dynamic ball-in-a-cup policies trained entirely in simulation. To the best of our knowledge, this result constitutes the first successful sim-to-real transfer for a four-degrees-of-freedom muscle-actuated robot arm.","one_line_summary":"GeAN learns actuator dynamics from position trajectories to enable successful sim-to-real transfer of goal-reaching and ball-in-a-cup policies on a 4-DoF pneumatic muscle-actuated robot, reported as the first such transfer for this system type.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a neural network trained solely on joint position trajectories can capture the nonlinear actuator dynamics (friction, hysteresis) with sufficient accuracy to enable zero-shot policy transfer from the hybrid simulation to the physical robot without torque sensing or additional adaptation.","pith_extraction_headline":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09487/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":"f0908cb4-f915-4f69-9a00-e2e79c636ebb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"061daCYUbQ70qTfJxJV5HSnNpi2g5h9QXj/PbhqvcNAKCJsaE1aIkrjYn7e2wvwS+1zUW2gnunU5f3B6quXYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:23:48.431239Z"},"content_sha256":"0b4912d2ddf736e44db72239678a74bf85186d9a1f4f547b308b7379786c3ed8","schema_version":"1.0","event_id":"sha256:0b4912d2ddf736e44db72239678a74bf85186d9a1f4f547b308b7379786c3ed8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/bundle.json","state_url":"https://pith.science/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/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":"2026-06-04T19:23:48Z","links":{"resolver":"https://pith.science/pith/BN4P6QA5PG3YB5GI6OR66C2AQK","bundle":"https://pith.science/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/bundle.json","state":"https://pith.science/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BN4P6QA5PG3YB5GI6OR66C2AQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BN4P6QA5PG3YB5GI6OR66C2AQK","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":"383b8d823224d140c3ec76d7ee142a4e5a04776252f74690b5d11f705b20ca02","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T16:52:54Z","title_canon_sha256":"4d3db323fa786e629f2692740a55f79c5dab4845ccc1c51f07af94aae6634ae3"},"schema_version":"1.0","source":{"id":"2604.09487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09487","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09487v2","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09487","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"BN4P6QA5PG3Y","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"BN4P6QA5PG3YB5GI","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"BN4P6QA5","created_at":"2026-06-02T02:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:0b4912d2ddf736e44db72239678a74bf85186d9a1f4f547b308b7379786c3ed8","target":"graph","created_at":"2026-06-02T02:04:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Using GeAN on PAMY2, a tendon-driven robot powered by pneumatic artificial muscles, we successfully deploy precise goal-reaching and dynamic ball-in-a-cup policies trained entirely in simulation. To the best of our knowledge, this result constitutes the first successful sim-to-real transfer for a four-degrees-of-freedom muscle-actuated robot arm."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a neural network trained solely on joint position trajectories can capture the nonlinear actuator dynamics (friction, hysteresis) with sufficient accuracy to enable zero-shot policy transfer from the hybrid simulation to the physical robot without torque sensing or additional adaptation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GeAN learns actuator dynamics from position trajectories to enable successful sim-to-real transfer of goal-reaching and ball-in-a-cup policies on a 4-DoF pneumatic muscle-actuated robot, reported as the first such transfer for this system type."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot."}],"snapshot_sha256":"22f9cd768e05f41bfb3126dc2e45d146c608acdf1e386cdb8af5f20e1d6572b8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition. Still, these systems are rarely used in practice due to inherent nonlinearities, friction, and hysteresis, which complicate modeling and control. So far, these challenges have hindered policy transfer from simulation to real systems. To bridge this gap, we propose a sim-to-real pipeline that learns a neural network model of this complex actuation and leverages established rigid body simulation for the arm dynamics and interactions with the environment. Our method, ca","authors_text":"Bernhard Sch\\\"olkopf, Dieter B\\\"uchler, Ingmar Posner, Jan Schneider, Le Chen, Mridul Mahajan, Simon Guist","cross_cats":["cs.LG"],"headline":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T16:52:54Z","title":"Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09487","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:49:19.078419Z","id":"f0908cb4-f915-4f69-9a00-e2e79c636ebb","model_set":{"reader":"grok-4.3"},"one_line_summary":"GeAN learns actuator dynamics from position trajectories to enable successful sim-to-real transfer of goal-reaching and ball-in-a-cup policies on a 4-DoF pneumatic muscle-actuated robot, reported as the first such transfer for this system type.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Neural network models nonlinear muscle actuation from position data to enable sim-to-real policy transfer on tendon-driven robot.","strongest_claim":"Using GeAN on PAMY2, a tendon-driven robot powered by pneumatic artificial muscles, we successfully deploy precise goal-reaching and dynamic ball-in-a-cup policies trained entirely in simulation. To the best of our knowledge, this result constitutes the first successful sim-to-real transfer for a four-degrees-of-freedom muscle-actuated robot arm.","weakest_assumption":"That a neural network trained solely on joint position trajectories can capture the nonlinear actuator dynamics (friction, hysteresis) with sufficient accuracy to enable zero-shot policy transfer from the hybrid simulation to the physical robot without torque sensing or additional adaptation."}},"verdict_id":"f0908cb4-f915-4f69-9a00-e2e79c636ebb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bc16813c9dfbbe846ccac04eef0c4bfc0b9af5adfe126ddbac6e151963e030e7","target":"record","created_at":"2026-06-02T02:04:17Z","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":"383b8d823224d140c3ec76d7ee142a4e5a04776252f74690b5d11f705b20ca02","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T16:52:54Z","title_canon_sha256":"4d3db323fa786e629f2692740a55f79c5dab4845ccc1c51f07af94aae6634ae3"},"schema_version":"1.0","source":{"id":"2604.09487","kind":"arxiv","version":2}},"canonical_sha256":"0b78ff401d79b780f4c8f3a3ef0b4082984da59798f69217f9dc503fafcc691c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b78ff401d79b780f4c8f3a3ef0b4082984da59798f69217f9dc503fafcc691c","first_computed_at":"2026-06-02T02:04:17.329467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:17.329467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BXl7ynIiogWK404UYKkxdwhpRyzv/qqcbCBtUW6GLH0HZKYpSw8/K+w9tUEeoeY4J9cT8FNHxLmmgY8JhvQlBg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:17.330020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc16813c9dfbbe846ccac04eef0c4bfc0b9af5adfe126ddbac6e151963e030e7","sha256:0b4912d2ddf736e44db72239678a74bf85186d9a1f4f547b308b7379786c3ed8"],"state_sha256":"d04510afd8639478afd510af5451b8f997293394a2f0a4700590f11941d5fc09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CeMbJRjAeep5eEJhhEes7NG2I7PPJkLyNbHhMhS740CACBnDnjB/wUHToPOCedIJUViv2b2ib1QdWJ+AuJW3Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T19:23:48.434290Z","bundle_sha256":"5879565f99a7303570d7acc9dd1eadc049359e654496e4fe052ce01c04a1a83d"}}