{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3XO5U3KERUFSJ3PYFEFPX5J3QO","short_pith_number":"pith:3XO5U3KE","canonical_record":{"source":{"id":"2510.10759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T18:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"73add6ec2ddd19d8e8bee966f09cfc80ab21db788ac55175be0e9758dbef053c","abstract_canon_sha256":"3e8b4f7b0d219e61be7b16b63bf12830618ec9bf98811a3eb5689b152b8443dd"},"schema_version":"1.0"},"canonical_sha256":"ddddda6d448d0b24edf8290afbf53b839aff317ae7c37c1166065929a8df4858","source":{"kind":"arxiv","id":"2510.10759","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10759","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10759v2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10759","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"3XO5U3KERUFS","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"3XO5U3KERUFSJ3PY","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"3XO5U3KE","created_at":"2026-06-23T02:13:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3XO5U3KERUFSJ3PYFEFPX5J3QO","target":"record","payload":{"canonical_record":{"source":{"id":"2510.10759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T18:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"73add6ec2ddd19d8e8bee966f09cfc80ab21db788ac55175be0e9758dbef053c","abstract_canon_sha256":"3e8b4f7b0d219e61be7b16b63bf12830618ec9bf98811a3eb5689b152b8443dd"},"schema_version":"1.0"},"canonical_sha256":"ddddda6d448d0b24edf8290afbf53b839aff317ae7c37c1166065929a8df4858","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:17.542794Z","signature_b64":"oOHXwrQ4rKqjTjXJHk5CCfhshzLkDB1HANrz7lU4ebuYzJCL+vzR5Mq5IL2CEnaqml31FGs6jgB8PHe7WWDJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddddda6d448d0b24edf8290afbf53b839aff317ae7c37c1166065929a8df4858","last_reissued_at":"2026-06-23T02:13:17.542326Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:17.542326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.10759","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":"2026-06-23T02:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svxDFvvnRzGyZuRllxClC9kvJaEzOLvulCThkNcyye48D2A2i5bLvIJwAqCEhVNAUiYAw1iEk1BHWGrlma20CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:42:31.968578Z"},"content_sha256":"aba06421a2458fc45f1dde6b0eebfd2fcc743c941c96e9fec9648727ba24f1d8","schema_version":"1.0","event_id":"sha256:aba06421a2458fc45f1dde6b0eebfd2fcc743c941c96e9fec9648727ba24f1d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3XO5U3KERUFSJ3PYFEFPX5J3QO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Arthicha Srisuchinnawong, Poramate Manoonpong","submitted_at":"2025-10-12T18:58:59Z","abstract_excerpt":"Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address both issues by proposing Reward-Oriented Gains via Embodied Regulation (ROGER), which adapts reward-weighting gains online based on penalties received throughout the embodied interaction process. The ratio between the positive reward (primary reward) and negative reward (penalty) gains is automatically reduced as the learning approaches the constraint thresh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10759","kind":"arxiv","version":2},"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/2510.10759/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":"2026-06-23T02:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EUYXDewdKCsc0P1BwPMvw2Xx4DxNwxLo564QuD6DgmdFAl7iikEUEQofUxeZU4WQxkEB3uLZhLstJO6eGUDdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:42:31.968947Z"},"content_sha256":"cc98e60a138ffe631bf5fec4da3d00276a63f24752bfe9f0bbc23287c3dc31cb","schema_version":"1.0","event_id":"sha256:cc98e60a138ffe631bf5fec4da3d00276a63f24752bfe9f0bbc23287c3dc31cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/bundle.json","state_url":"https://pith.science/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/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":"2026-06-29T19:42:31Z","links":{"resolver":"https://pith.science/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO","bundle":"https://pith.science/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/bundle.json","state":"https://pith.science/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XO5U3KERUFSJ3PYFEFPX5J3QO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3XO5U3KERUFSJ3PYFEFPX5J3QO","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":"3e8b4f7b0d219e61be7b16b63bf12830618ec9bf98811a3eb5689b152b8443dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T18:58:59Z","title_canon_sha256":"73add6ec2ddd19d8e8bee966f09cfc80ab21db788ac55175be0e9758dbef053c"},"schema_version":"1.0","source":{"id":"2510.10759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10759","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10759v2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10759","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"3XO5U3KERUFS","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"3XO5U3KERUFSJ3PY","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"3XO5U3KE","created_at":"2026-06-23T02:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:cc98e60a138ffe631bf5fec4da3d00276a63f24752bfe9f0bbc23287c3dc31cb","target":"graph","created_at":"2026-06-23T02:13:17Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.10759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address both issues by proposing Reward-Oriented Gains via Embodied Regulation (ROGER), which adapts reward-weighting gains online based on penalties received throughout the embodied interaction process. The ratio between the positive reward (primary reward) and negative reward (penalty) gains is automatically reduced as the learning approaches the constraint thresh","authors_text":"Arthicha Srisuchinnawong, Poramate Manoonpong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T18:58:59Z","title":"Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10759","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:aba06421a2458fc45f1dde6b0eebfd2fcc743c941c96e9fec9648727ba24f1d8","target":"record","created_at":"2026-06-23T02:13:17Z","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":"3e8b4f7b0d219e61be7b16b63bf12830618ec9bf98811a3eb5689b152b8443dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T18:58:59Z","title_canon_sha256":"73add6ec2ddd19d8e8bee966f09cfc80ab21db788ac55175be0e9758dbef053c"},"schema_version":"1.0","source":{"id":"2510.10759","kind":"arxiv","version":2}},"canonical_sha256":"ddddda6d448d0b24edf8290afbf53b839aff317ae7c37c1166065929a8df4858","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddddda6d448d0b24edf8290afbf53b839aff317ae7c37c1166065929a8df4858","first_computed_at":"2026-06-23T02:13:17.542326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:17.542326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oOHXwrQ4rKqjTjXJHk5CCfhshzLkDB1HANrz7lU4ebuYzJCL+vzR5Mq5IL2CEnaqml31FGs6jgB8PHe7WWDJBQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:17.542794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.10759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aba06421a2458fc45f1dde6b0eebfd2fcc743c941c96e9fec9648727ba24f1d8","sha256:cc98e60a138ffe631bf5fec4da3d00276a63f24752bfe9f0bbc23287c3dc31cb"],"state_sha256":"25f29e176bfdfd925f083b9dc21194fd4522bc56f79de57045933274d51e3d0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGVlgHXLkiFbJc8uZbGxe8a2ppCeUEOJBgs3+RlH0blH0xUs0D7ZkmTSoopI/IX0l1JzKhkf8Taj1h+lgKl6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:42:31.970847Z","bundle_sha256":"a8f8f41b5373d42e18b84192604923d449a5fa201549b9a78f041094bc3a3118"}}