{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H7F353VDKFHD5EUMCIBTRU74UV","short_pith_number":"pith:H7F353VD","canonical_record":{"source":{"id":"2509.01765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-01T20:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1d9e35154c7da30156386c091735c2d01a6e5bdf6a438102c2be3d8313043e5","abstract_canon_sha256":"e85c7cab3857f234ac8f11797fe40db05580c349ee2cf282ac1615ff23ef88d0"},"schema_version":"1.0"},"canonical_sha256":"3fcbbeeea3514e3e928c120338d3fca54682a22f1846c5fdbc9061cd491a3134","source":{"kind":"arxiv","id":"2509.01765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01765","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01765v1","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01765","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"H7F353VDKFHD","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"H7F353VDKFHD5EUM","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"H7F353VD","created_at":"2026-07-05T12:03:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H7F353VDKFHD5EUMCIBTRU74UV","target":"record","payload":{"canonical_record":{"source":{"id":"2509.01765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-01T20:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1d9e35154c7da30156386c091735c2d01a6e5bdf6a438102c2be3d8313043e5","abstract_canon_sha256":"e85c7cab3857f234ac8f11797fe40db05580c349ee2cf282ac1615ff23ef88d0"},"schema_version":"1.0"},"canonical_sha256":"3fcbbeeea3514e3e928c120338d3fca54682a22f1846c5fdbc9061cd491a3134","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:07.771412Z","signature_b64":"O2AgT+7qfuYPiFiHHbCAR3K4vjVOEvkeylguH4i5TM/hX4caGxyBSlUBCqPtJwuXDlt64vM/QvHdNG1q/hOaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fcbbeeea3514e3e928c120338d3fca54682a22f1846c5fdbc9061cd491a3134","last_reissued_at":"2026-07-05T12:03:07.770792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:07.770792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.01765","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":"2026-07-05T12:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/IJy/C51lqcGuJk3akGUklIeCnk/yzf5pM/Xmk2AQwNEU6cgu6PCBZpXoHV4SypaL4KjvwlXAfH7S+jTGGtDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:01:58.157956Z"},"content_sha256":"da018db0cc251d13dcc78e0ec6e302461bca3bbbe48791620a7b25ac7f439152","schema_version":"1.0","event_id":"sha256:da018db0cc251d13dcc78e0ec6e302461bca3bbbe48791620a7b25ac7f439152"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H7F353VDKFHD5EUMCIBTRU74UV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Akhil Perincherry, Bikram Pandit, Skand Peri, Stefan Lee","submitted_at":"2025-09-01T20:52:41Z","abstract_excerpt":"Efficient robot control often requires balancing task performance with energy expenditure. A common approach in reinforcement learning (RL) is to penalize energy use directly as part of the reward function. This requires carefully tuning weight terms to avoid undesirable trade-offs where energy minimization harms task success. In this work, we propose a hyperparameter-free gradient optimization method to minimize energy expenditure without conflicting with task performance. Inspired by recent works in multitask learning, our method applies policy gradient projection between task and energy obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01765","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/2509.01765/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":"2026-07-05T12:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pv0QuIeib43I8dKzdDkswFE1RK9EcHatwgRpUGBRZcTUyKz8gNITyfJWxjTkFFFPehW2vEkUOLWT0h7CYzxEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:01:58.158335Z"},"content_sha256":"c35d74dc1011643148df501d7444794fb96e1ecad261c225a7b2107077e0efb8","schema_version":"1.0","event_id":"sha256:c35d74dc1011643148df501d7444794fb96e1ecad261c225a7b2107077e0efb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H7F353VDKFHD5EUMCIBTRU74UV/bundle.json","state_url":"https://pith.science/pith/H7F353VDKFHD5EUMCIBTRU74UV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H7F353VDKFHD5EUMCIBTRU74UV/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":"2026-07-07T06:01:58Z","links":{"resolver":"https://pith.science/pith/H7F353VDKFHD5EUMCIBTRU74UV","bundle":"https://pith.science/pith/H7F353VDKFHD5EUMCIBTRU74UV/bundle.json","state":"https://pith.science/pith/H7F353VDKFHD5EUMCIBTRU74UV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H7F353VDKFHD5EUMCIBTRU74UV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H7F353VDKFHD5EUMCIBTRU74UV","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":"e85c7cab3857f234ac8f11797fe40db05580c349ee2cf282ac1615ff23ef88d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-01T20:52:41Z","title_canon_sha256":"c1d9e35154c7da30156386c091735c2d01a6e5bdf6a438102c2be3d8313043e5"},"schema_version":"1.0","source":{"id":"2509.01765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01765","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01765v1","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01765","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"H7F353VDKFHD","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"H7F353VDKFHD5EUM","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"H7F353VD","created_at":"2026-07-05T12:03:07Z"}],"graph_snapshots":[{"event_id":"sha256:c35d74dc1011643148df501d7444794fb96e1ecad261c225a7b2107077e0efb8","target":"graph","created_at":"2026-07-05T12:03:07Z","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/2509.01765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient robot control often requires balancing task performance with energy expenditure. A common approach in reinforcement learning (RL) is to penalize energy use directly as part of the reward function. This requires carefully tuning weight terms to avoid undesirable trade-offs where energy minimization harms task success. In this work, we propose a hyperparameter-free gradient optimization method to minimize energy expenditure without conflicting with task performance. Inspired by recent works in multitask learning, our method applies policy gradient projection between task and energy obj","authors_text":"Akhil Perincherry, Bikram Pandit, Skand Peri, Stefan Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-01T20:52:41Z","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01765","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:da018db0cc251d13dcc78e0ec6e302461bca3bbbe48791620a7b25ac7f439152","target":"record","created_at":"2026-07-05T12:03:07Z","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":"e85c7cab3857f234ac8f11797fe40db05580c349ee2cf282ac1615ff23ef88d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-01T20:52:41Z","title_canon_sha256":"c1d9e35154c7da30156386c091735c2d01a6e5bdf6a438102c2be3d8313043e5"},"schema_version":"1.0","source":{"id":"2509.01765","kind":"arxiv","version":1}},"canonical_sha256":"3fcbbeeea3514e3e928c120338d3fca54682a22f1846c5fdbc9061cd491a3134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fcbbeeea3514e3e928c120338d3fca54682a22f1846c5fdbc9061cd491a3134","first_computed_at":"2026-07-05T12:03:07.770792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:07.770792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O2AgT+7qfuYPiFiHHbCAR3K4vjVOEvkeylguH4i5TM/hX4caGxyBSlUBCqPtJwuXDlt64vM/QvHdNG1q/hOaBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:07.771412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da018db0cc251d13dcc78e0ec6e302461bca3bbbe48791620a7b25ac7f439152","sha256:c35d74dc1011643148df501d7444794fb96e1ecad261c225a7b2107077e0efb8"],"state_sha256":"dc8aa809d88cdf1a73be4dfb50573f61dd9b2dc8509567f4ca5e5f06e45a53ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzHD6LSgYq0bZWjAln+h5zZLEFcerziRq6a1ccxVvCgwaXPhWmw26u/V7Hq/psrymxaHdYoZz72tz5nLd8j6BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:01:58.160379Z","bundle_sha256":"c6e56c8b974d34a3762f164009148d931409065c384ea33ec6877a7a7d33e1c5"}}