{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:227NWNLEVCHIMQS4GAKCAH5SPZ","short_pith_number":"pith:227NWNLE","canonical_record":{"source":{"id":"2309.06687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b373bee2a6cdb7ea7153b22ba0f76d3c5e01a4b67be99f41f3f1fc82e7c60930","abstract_canon_sha256":"f347ff99dfecfcc8beaa6c2ba54beee6b5fbb8ef7771c05d1a773762c8c737b9"},"schema_version":"1.0"},"canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","source":{"kind":"arxiv","id":"2309.06687","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06687","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06687v2","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06687","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"227NWNLEVCHI","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"227NWNLEVCHIMQS4","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"227NWNLE","created_at":"2026-07-05T06:56:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:227NWNLEVCHIMQS4GAKCAH5SPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b373bee2a6cdb7ea7153b22ba0f76d3c5e01a4b67be99f41f3f1fc82e7c60930","abstract_canon_sha256":"f347ff99dfecfcc8beaa6c2ba54beee6b5fbb8ef7771c05d1a773762c8c737b9"},"schema_version":"1.0"},"canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:22.432457Z","signature_b64":"lkWkIZqkbsQHZDUZksfLy0BCyUH8KUARr8f2Lyte8pP5NbRen3qqk1grYwgUxHffUuVlev4zIwAeFckuBnQyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","last_reissued_at":"2026-07-05T06:56:22.431998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:22.431998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06687","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":"2026-07-05T06:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06j71iEtpknYGJ/XEh5LpZpSMbyUvjSbY1tJ1yT8rpjffkrINs55QBSELYJ6EpYMNwUQRzU9kQbD9Drh4884Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:25:06.916674Z"},"content_sha256":"b91c8906f05e612dd370e413f611e2b79943bf6491842be62dd74057eb426a05","schema_version":"1.0","event_id":"sha256:b91c8906f05e612dd370e413f611e2b79943bf6491842be62dd74057eb426a05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:227NWNLEVCHIMQS4GAKCAH5SPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chunrong Fang, Jiawei Liu, Jiayang Song, Lei Ma, Zhan Shu, Zhehua Zhou","submitted_at":"2023-09-13T02:56:56Z","abstract_excerpt":"Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06687","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/2309.06687/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":"2026-07-05T06:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Whtqchiuv+X6ISTq0fSm84CpZjPKSaHaN5agUdnLFqAS4DoxqWWfNXH/PEP52RC9VvKm8PCzqSaeEcvHrkdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:25:06.917207Z"},"content_sha256":"df4bb2d31f766f54b83d644c5b82bddb1b8b30718e9fac71d1c04f36a63c370a","schema_version":"1.0","event_id":"sha256:df4bb2d31f766f54b83d644c5b82bddb1b8b30718e9fac71d1c04f36a63c370a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/bundle.json","state_url":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/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":"2026-08-08T12:25:06Z","links":{"resolver":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ","bundle":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/bundle.json","state":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:227NWNLEVCHIMQS4GAKCAH5SPZ","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":"f347ff99dfecfcc8beaa6c2ba54beee6b5fbb8ef7771c05d1a773762c8c737b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","title_canon_sha256":"b373bee2a6cdb7ea7153b22ba0f76d3c5e01a4b67be99f41f3f1fc82e7c60930"},"schema_version":"1.0","source":{"id":"2309.06687","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06687","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06687v2","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06687","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"227NWNLEVCHI","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"227NWNLEVCHIMQS4","created_at":"2026-07-05T06:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"227NWNLE","created_at":"2026-07-05T06:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:df4bb2d31f766f54b83d644c5b82bddb1b8b30718e9fac71d1c04f36a63c370a","target":"graph","created_at":"2026-07-05T06:56:22Z","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/2309.06687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refi","authors_text":"Chunrong Fang, Jiawei Liu, Jiayang Song, Lei Ma, Zhan Shu, Zhehua Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06687","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:b91c8906f05e612dd370e413f611e2b79943bf6491842be62dd74057eb426a05","target":"record","created_at":"2026-07-05T06:56:22Z","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":"f347ff99dfecfcc8beaa6c2ba54beee6b5fbb8ef7771c05d1a773762c8c737b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","title_canon_sha256":"b373bee2a6cdb7ea7153b22ba0f76d3c5e01a4b67be99f41f3f1fc82e7c60930"},"schema_version":"1.0","source":{"id":"2309.06687","kind":"arxiv","version":2}},"canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","first_computed_at":"2026-07-05T06:56:22.431998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:22.431998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lkWkIZqkbsQHZDUZksfLy0BCyUH8KUARr8f2Lyte8pP5NbRen3qqk1grYwgUxHffUuVlev4zIwAeFckuBnQyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:22.432457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06687","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b91c8906f05e612dd370e413f611e2b79943bf6491842be62dd74057eb426a05","sha256:df4bb2d31f766f54b83d644c5b82bddb1b8b30718e9fac71d1c04f36a63c370a"],"state_sha256":"bbbc2475a10c46849a021b2758bae8bf1f3fbf4a1522e0cfb24942dcf94c144d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGv3WNtGTl1cD6I09TPIeG7q6Q2sZV9M3wdQgemT+GHjMwU+W+XD3eX8rnVEEYO+K+QBBSW47uspFnUd5BJTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:25:06.920993Z","bundle_sha256":"47ef15882a2de50d1457daff751dabd2d56c05c40b501e81c99c00e808d99705"}}