{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TYL4ZMKGASPTRMDDC7KXOBN3VK","short_pith_number":"pith:TYL4ZMKG","canonical_record":{"source":{"id":"2505.02483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-05T09:06:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99e19e371d6ad7fb4094c83d85b4817dc355cf9710cdbe3e5edacee75eca4003","abstract_canon_sha256":"8bf398b82248b2df42e08322a375d03e2a201e2b6141a7ea4d312bb16a57ae46"},"schema_version":"1.0"},"canonical_sha256":"9e17ccb146049f38b06317d57705bbaa8a5ef2688618578b6c6efb741ba8cbdb","source":{"kind":"arxiv","id":"2505.02483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02483","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02483v1","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02483","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_12","alias_value":"TYL4ZMKGASPT","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_16","alias_value":"TYL4ZMKGASPTRMDD","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_8","alias_value":"TYL4ZMKG","created_at":"2026-07-05T10:58:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TYL4ZMKGASPTRMDDC7KXOBN3VK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-05T09:06:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99e19e371d6ad7fb4094c83d85b4817dc355cf9710cdbe3e5edacee75eca4003","abstract_canon_sha256":"8bf398b82248b2df42e08322a375d03e2a201e2b6141a7ea4d312bb16a57ae46"},"schema_version":"1.0"},"canonical_sha256":"9e17ccb146049f38b06317d57705bbaa8a5ef2688618578b6c6efb741ba8cbdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:37.755287Z","signature_b64":"95u+76Lp+hfGkT/t/bKakLtd9j8S3LaCFnq+Znt1w38RDL9oGtlQqjQgGGyYzX0pt6NCbHGSFUPS1wM4ZPnRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e17ccb146049f38b06317d57705bbaa8a5ef2688618578b6c6efb741ba8cbdb","last_reissued_at":"2026-07-05T10:58:37.754796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:37.754796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02483","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":"2026-07-05T10:58:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"As6pgcalss3UIuR2LkvcEMl6MyTWwmMmqUYTXg22EQcOPhrpORrrlN3oYqxCLaWfZL7mU8awwrxdc29yRVlvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:33:41.588667Z"},"content_sha256":"47f9b35daa8298e88b9fa1fded476562d3b2d92e8f56c8453826b5a468ec6b23","schema_version":"1.0","event_id":"sha256:47f9b35daa8298e88b9fa1fded476562d3b2d92e8f56c8453826b5a468ec6b23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TYL4ZMKGASPTRMDDC7KXOBN3VK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Changxin Huang, Jianqiang Li, Jingzhao Xu, Junyang Liang, Yanbin Chang","submitted_at":"2025-05-05T09:06:17Z","abstract_excerpt":"Enabling a high-degree-of-freedom robot to learn specific skills is a challenging task due to the complexity of robotic dynamics. Reinforcement learning (RL) has emerged as a promising solution; however, addressing such problems requires the design of multiple reward functions to account for various constraints in robotic motion. Existing approaches typically sum all reward components indiscriminately to optimize the RL value function and policy. We argue that this uniform inclusion of all reward components in policy optimization is inefficient and limits the robot's learning performance. To a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02483","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/2505.02483/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":"2026-07-05T10:58:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71LvqnXYoIsUo07nD0PYiuPt+YUfc1+5rl7vP9BBGMdk6sKdjg9KTPOaqbKYYF5EVSNxr/vQo5aIpxBmNEI3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:33:41.589019Z"},"content_sha256":"83cfe9da61df950e84602563bad6e3201fa1b438da35e99c173bc63959aad119","schema_version":"1.0","event_id":"sha256:83cfe9da61df950e84602563bad6e3201fa1b438da35e99c173bc63959aad119"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/bundle.json","state_url":"https://pith.science/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/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":"2026-08-18T09:33:41Z","links":{"resolver":"https://pith.science/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK","bundle":"https://pith.science/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/bundle.json","state":"https://pith.science/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYL4ZMKGASPTRMDDC7KXOBN3VK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYL4ZMKGASPTRMDDC7KXOBN3VK","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":"8bf398b82248b2df42e08322a375d03e2a201e2b6141a7ea4d312bb16a57ae46","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-05T09:06:17Z","title_canon_sha256":"99e19e371d6ad7fb4094c83d85b4817dc355cf9710cdbe3e5edacee75eca4003"},"schema_version":"1.0","source":{"id":"2505.02483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02483","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02483v1","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02483","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_12","alias_value":"TYL4ZMKGASPT","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_16","alias_value":"TYL4ZMKGASPTRMDD","created_at":"2026-07-05T10:58:37Z"},{"alias_kind":"pith_short_8","alias_value":"TYL4ZMKG","created_at":"2026-07-05T10:58:37Z"}],"graph_snapshots":[{"event_id":"sha256:83cfe9da61df950e84602563bad6e3201fa1b438da35e99c173bc63959aad119","target":"graph","created_at":"2026-07-05T10:58:37Z","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/2505.02483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enabling a high-degree-of-freedom robot to learn specific skills is a challenging task due to the complexity of robotic dynamics. Reinforcement learning (RL) has emerged as a promising solution; however, addressing such problems requires the design of multiple reward functions to account for various constraints in robotic motion. Existing approaches typically sum all reward components indiscriminately to optimize the RL value function and policy. We argue that this uniform inclusion of all reward components in policy optimization is inefficient and limits the robot's learning performance. To a","authors_text":"Changxin Huang, Jianqiang Li, Jingzhao Xu, Junyang Liang, Yanbin Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-05T09:06:17Z","title":"Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02483","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":"sha256:47f9b35daa8298e88b9fa1fded476562d3b2d92e8f56c8453826b5a468ec6b23","target":"record","created_at":"2026-07-05T10:58:37Z","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":"8bf398b82248b2df42e08322a375d03e2a201e2b6141a7ea4d312bb16a57ae46","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-05T09:06:17Z","title_canon_sha256":"99e19e371d6ad7fb4094c83d85b4817dc355cf9710cdbe3e5edacee75eca4003"},"schema_version":"1.0","source":{"id":"2505.02483","kind":"arxiv","version":1}},"canonical_sha256":"9e17ccb146049f38b06317d57705bbaa8a5ef2688618578b6c6efb741ba8cbdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e17ccb146049f38b06317d57705bbaa8a5ef2688618578b6c6efb741ba8cbdb","first_computed_at":"2026-07-05T10:58:37.754796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:37.754796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95u+76Lp+hfGkT/t/bKakLtd9j8S3LaCFnq+Znt1w38RDL9oGtlQqjQgGGyYzX0pt6NCbHGSFUPS1wM4ZPnRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:37.755287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47f9b35daa8298e88b9fa1fded476562d3b2d92e8f56c8453826b5a468ec6b23","sha256:83cfe9da61df950e84602563bad6e3201fa1b438da35e99c173bc63959aad119"],"state_sha256":"614c893a3b9c93bf9c35bef93253ae43c054f91f9e036a092516c3ee8f7f22aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0woo5cydoDiYohPchKYUmORbB5EfrLgpId2TgMJzWTJMHNHGE1/0WlpQ1S2eLebM8KLzHTM1aJPXQoWvih/cAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:33:41.592656Z","bundle_sha256":"562b54a4cddbaaa8f7836878cd131d847df866a0439f183d23ddb3fab793d849"}}