{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KE3EBX6O2PC3ROU3C5YS4HXSI2","short_pith_number":"pith:KE3EBX6O","canonical_record":{"source":{"id":"2606.26392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T21:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"8357aa4f80a9e363ea7ab3211bd87e2af21a4bdc452e0b6ac9104d9e40825886","abstract_canon_sha256":"5d8cd0c8b458353fade9d82f93efa523899bc4311a09cae079deadd5ac32e304"},"schema_version":"1.0"},"canonical_sha256":"513640dfced3c5b8ba9b17712e1ef2468e7a5bfae4fe08988cd1a759d78e63c2","source":{"kind":"arxiv","id":"2606.26392","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26392","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26392v1","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26392","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"KE3EBX6O2PC3","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"KE3EBX6O2PC3ROU3","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"KE3EBX6O","created_at":"2026-06-26T00:15:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KE3EBX6O2PC3ROU3C5YS4HXSI2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.26392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T21:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"8357aa4f80a9e363ea7ab3211bd87e2af21a4bdc452e0b6ac9104d9e40825886","abstract_canon_sha256":"5d8cd0c8b458353fade9d82f93efa523899bc4311a09cae079deadd5ac32e304"},"schema_version":"1.0"},"canonical_sha256":"513640dfced3c5b8ba9b17712e1ef2468e7a5bfae4fe08988cd1a759d78e63c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:39.736165Z","signature_b64":"Iz0kqbkyOthPvQ+eIa1MGH1NrC4K4nMIoTrQuyPmhw5oNMnGwxVYQN89L3lPlpa9PCpWClHVPNQDcqw0zWW+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"513640dfced3c5b8ba9b17712e1ef2468e7a5bfae4fe08988cd1a759d78e63c2","last_reissued_at":"2026-06-26T00:15:39.735619Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:39.735619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.26392","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":"2026-06-26T00:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wWrb/hNFNQdekeb7mV14vcfEMGsIWcyIA+2CybciH3dCOcw0m3MkmCeiRI44eL+vZBpYpVhWOdRdLDKjr8EtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:16:10.109772Z"},"content_sha256":"a00f8c445398cf5e73a6080c54e10206933dfd08bcc3bb124e8bd33b14ad79e7","schema_version":"1.0","event_id":"sha256:a00f8c445398cf5e73a6080c54e10206933dfd08bcc3bb124e8bd33b14ad79e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KE3EBX6O2PC3ROU3C5YS4HXSI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brian Plancher (Dartmouth College), Roy Xing (Dartmouth College), Seyoung Ree (Harvard University)","submitted_at":"2026-06-24T21:23:22Z","abstract_excerpt":"Reinforcement learning (RL) for locomotion frequently converges to locally optimal but undeployable behaviors, such as vibrating limbs or scooting on the torso, that maximize return without producing a usable gait. We present MPC-Injection, a low-overhead method that steers RL toward a designer-preferred gait by inserting transitions into the replay buffer from a model predictive controller solving the same Markov decision process. Unlike reward shaping, MPC-Injection does not require redesigning the task reward, and unlike adversarial imitation learning, it adds no discriminator, no kinematic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26392","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/2606.26392/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":"2026-06-26T00:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XFVbzNFq8/pMucv9QBgKxjshFkKCU2rT4IFzR1tuXLGG41iqZ5Tr+aYqcBCSxb7h3ynBfSY5Rr9pj46mobMFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:16:10.110182Z"},"content_sha256":"102f309ebdd01516f06a0f5f02c52fe18fde5c0bd96e45a51deac1767311640c","schema_version":"1.0","event_id":"sha256:102f309ebdd01516f06a0f5f02c52fe18fde5c0bd96e45a51deac1767311640c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/bundle.json","state_url":"https://pith.science/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/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":"2026-06-26T08:16:10Z","links":{"resolver":"https://pith.science/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2","bundle":"https://pith.science/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/bundle.json","state":"https://pith.science/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KE3EBX6O2PC3ROU3C5YS4HXSI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KE3EBX6O2PC3ROU3C5YS4HXSI2","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":"5d8cd0c8b458353fade9d82f93efa523899bc4311a09cae079deadd5ac32e304","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T21:23:22Z","title_canon_sha256":"8357aa4f80a9e363ea7ab3211bd87e2af21a4bdc452e0b6ac9104d9e40825886"},"schema_version":"1.0","source":{"id":"2606.26392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26392","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26392v1","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26392","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"KE3EBX6O2PC3","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"KE3EBX6O2PC3ROU3","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"KE3EBX6O","created_at":"2026-06-26T00:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:102f309ebdd01516f06a0f5f02c52fe18fde5c0bd96e45a51deac1767311640c","target":"graph","created_at":"2026-06-26T00:15:39Z","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/2606.26392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for locomotion frequently converges to locally optimal but undeployable behaviors, such as vibrating limbs or scooting on the torso, that maximize return without producing a usable gait. We present MPC-Injection, a low-overhead method that steers RL toward a designer-preferred gait by inserting transitions into the replay buffer from a model predictive controller solving the same Markov decision process. Unlike reward shaping, MPC-Injection does not require redesigning the task reward, and unlike adversarial imitation learning, it adds no discriminator, no kinematic","authors_text":"Brian Plancher (Dartmouth College), Roy Xing (Dartmouth College), Seyoung Ree (Harvard University)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T21:23:22Z","title":"MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26392","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:a00f8c445398cf5e73a6080c54e10206933dfd08bcc3bb124e8bd33b14ad79e7","target":"record","created_at":"2026-06-26T00:15:39Z","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":"5d8cd0c8b458353fade9d82f93efa523899bc4311a09cae079deadd5ac32e304","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T21:23:22Z","title_canon_sha256":"8357aa4f80a9e363ea7ab3211bd87e2af21a4bdc452e0b6ac9104d9e40825886"},"schema_version":"1.0","source":{"id":"2606.26392","kind":"arxiv","version":1}},"canonical_sha256":"513640dfced3c5b8ba9b17712e1ef2468e7a5bfae4fe08988cd1a759d78e63c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"513640dfced3c5b8ba9b17712e1ef2468e7a5bfae4fe08988cd1a759d78e63c2","first_computed_at":"2026-06-26T00:15:39.735619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:39.735619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iz0kqbkyOthPvQ+eIa1MGH1NrC4K4nMIoTrQuyPmhw5oNMnGwxVYQN89L3lPlpa9PCpWClHVPNQDcqw0zWW+Dw==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:39.736165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00f8c445398cf5e73a6080c54e10206933dfd08bcc3bb124e8bd33b14ad79e7","sha256:102f309ebdd01516f06a0f5f02c52fe18fde5c0bd96e45a51deac1767311640c"],"state_sha256":"fbeea5b889a71be8d0b9ba85842d6fa8d32f6cac3844f39299c7e5a9166929ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxaS9r3yTmdC2TnX3XTssZRqieavjFqODHWSF0vfwZMx2tzMG33wuP+3aEckOEbnv/4EN9jGZTJgj534Iv/UAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T08:16:10.112874Z","bundle_sha256":"84017e68411ace0ba3a3ba5c909fbc2c05a9d1605d24d42022c7865afa60fd89"}}