{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q7NR3W66PQAEL4GMDWD52NSDN5","short_pith_number":"pith:Q7NR3W66","canonical_record":{"source":{"id":"2310.14092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-21T19:10:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f315bec09071fecb8093b3b18e1ca84f4651656085d1ec4615181c42799ac339","abstract_canon_sha256":"e3190cd29a8233b5a0b14b507121e15daab75881e527dbc6c7ce650bb4c6e299"},"schema_version":"1.0"},"canonical_sha256":"87db1ddbde7c0045f0cc1d87dd36436f4e289a9e746fabee47d96050914b71e6","source":{"kind":"arxiv","id":"2310.14092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14092","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14092v1","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14092","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q7NR3W66PQAE","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"Q7NR3W66PQAEL4GM","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"Q7NR3W66","created_at":"2026-07-05T07:03:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q7NR3W66PQAEL4GMDWD52NSDN5","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-21T19:10:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f315bec09071fecb8093b3b18e1ca84f4651656085d1ec4615181c42799ac339","abstract_canon_sha256":"e3190cd29a8233b5a0b14b507121e15daab75881e527dbc6c7ce650bb4c6e299"},"schema_version":"1.0"},"canonical_sha256":"87db1ddbde7c0045f0cc1d87dd36436f4e289a9e746fabee47d96050914b71e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:39.528155Z","signature_b64":"uRy9BAbRObh/AZURBvXSu/ujzQAKEcpPYT378oMpQlx2Ub6XRdAgwncECKErq4iLfHDYPqSJkjD36gRcx4fwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87db1ddbde7c0045f0cc1d87dd36436f4e289a9e746fabee47d96050914b71e6","last_reissued_at":"2026-07-05T07:03:39.527674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:39.527674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14092","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":"2026-07-05T07:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yjpv4OZHKCF77RPGTrLuy6B0rbW5tnmpbUi9dgxHlPRJoebQTdTuG+AYvlhdvFHyG6ZuUZHq9u6Gfp25ekewCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:30.609606Z"},"content_sha256":"42e78dd75d73dc529193478375a17271aa55d185621e14b48e98680e41938077","schema_version":"1.0","event_id":"sha256:42e78dd75d73dc529193478375a17271aa55d185621e14b48e98680e41938077"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q7NR3W66PQAEL4GMDWD52NSDN5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Reward for Physical Skills using Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Yiqing Xu, Yuwei Zeng","submitted_at":"2023-10-21T19:10:06Z","abstract_excerpt":"Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert demonstration data both costly and time-consuming. Large Language Models (LLMs) contain valuable task-related knowledge that can aid in learning these reward functions. However, the direct application of LLMs for proposing reward functions has its limitations such as numerical instability and inability to incorporate the environment feedback. We aim to extract task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14092","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/2310.14092/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":"2026-07-05T07:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1MjGrbwwOdNgVyCpWo/pBXU1EhvrwGBqS/WgjTG+yQDj31Jg1/dm9O4qP4XaxPT+diNagxEZ1U+FhLuWT+sDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:30.610093Z"},"content_sha256":"8d30b002b1453092f25d4db9cd7d667e0092cc18deb600aba4d000ca9065718e","schema_version":"1.0","event_id":"sha256:8d30b002b1453092f25d4db9cd7d667e0092cc18deb600aba4d000ca9065718e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/bundle.json","state_url":"https://pith.science/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/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":"2026-08-09T22:29:30Z","links":{"resolver":"https://pith.science/pith/Q7NR3W66PQAEL4GMDWD52NSDN5","bundle":"https://pith.science/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/bundle.json","state":"https://pith.science/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7NR3W66PQAEL4GMDWD52NSDN5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q7NR3W66PQAEL4GMDWD52NSDN5","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":"e3190cd29a8233b5a0b14b507121e15daab75881e527dbc6c7ce650bb4c6e299","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-21T19:10:06Z","title_canon_sha256":"f315bec09071fecb8093b3b18e1ca84f4651656085d1ec4615181c42799ac339"},"schema_version":"1.0","source":{"id":"2310.14092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14092","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14092v1","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14092","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q7NR3W66PQAE","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"Q7NR3W66PQAEL4GM","created_at":"2026-07-05T07:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"Q7NR3W66","created_at":"2026-07-05T07:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:8d30b002b1453092f25d4db9cd7d667e0092cc18deb600aba4d000ca9065718e","target":"graph","created_at":"2026-07-05T07:03:39Z","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/2310.14092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert demonstration data both costly and time-consuming. Large Language Models (LLMs) contain valuable task-related knowledge that can aid in learning these reward functions. However, the direct application of LLMs for proposing reward functions has its limitations such as numerical instability and inability to incorporate the environment feedback. We aim to extract task ","authors_text":"Yiqing Xu, Yuwei Zeng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-21T19:10:06Z","title":"Learning Reward for Physical Skills using Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14092","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":"sha256:42e78dd75d73dc529193478375a17271aa55d185621e14b48e98680e41938077","target":"record","created_at":"2026-07-05T07:03:39Z","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":"e3190cd29a8233b5a0b14b507121e15daab75881e527dbc6c7ce650bb4c6e299","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-21T19:10:06Z","title_canon_sha256":"f315bec09071fecb8093b3b18e1ca84f4651656085d1ec4615181c42799ac339"},"schema_version":"1.0","source":{"id":"2310.14092","kind":"arxiv","version":1}},"canonical_sha256":"87db1ddbde7c0045f0cc1d87dd36436f4e289a9e746fabee47d96050914b71e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87db1ddbde7c0045f0cc1d87dd36436f4e289a9e746fabee47d96050914b71e6","first_computed_at":"2026-07-05T07:03:39.527674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:39.527674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uRy9BAbRObh/AZURBvXSu/ujzQAKEcpPYT378oMpQlx2Ub6XRdAgwncECKErq4iLfHDYPqSJkjD36gRcx4fwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:39.528155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42e78dd75d73dc529193478375a17271aa55d185621e14b48e98680e41938077","sha256:8d30b002b1453092f25d4db9cd7d667e0092cc18deb600aba4d000ca9065718e"],"state_sha256":"24ace42fa52a29b2004585767bc48c9367a4b309a6db2c592559adae4dfdac0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sD6IZ/2nQxMqxKqnDIPk8paruJxoMBiGCsU8EJ/5aUxBsyXdABcXGFfHkY787YkO1VlxsLVWVpordW2ZsDEMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:29:30.614055Z","bundle_sha256":"27b32abc23afe24d2ea060c1a3af75dcb1e5976911b4550e3117d3b09e65b7a6"}}