{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GNGNELMZKLUGEHXXVLJ35AU2ST","short_pith_number":"pith:GNGNELMZ","canonical_record":{"source":{"id":"2410.09187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T18:41:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"332df6faa9b0535e1cadd4c75f6f894f12cb832220cb5fa98c60bbc822c082f0","abstract_canon_sha256":"964780e1982c23220f37d049c80292db028eabf3d23cd768e0566b4afd73c055"},"schema_version":"1.0"},"canonical_sha256":"334cd22d9952e8621ef7aad3be829a94dbc9b5029e775e1d71e2bb1eb002d1b8","source":{"kind":"arxiv","id":"2410.09187","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09187","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09187v2","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09187","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"GNGNELMZKLUG","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"GNGNELMZKLUGEHXX","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"GNGNELMZ","created_at":"2026-07-05T09:25:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GNGNELMZKLUGEHXXVLJ35AU2ST","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T18:41:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"332df6faa9b0535e1cadd4c75f6f894f12cb832220cb5fa98c60bbc822c082f0","abstract_canon_sha256":"964780e1982c23220f37d049c80292db028eabf3d23cd768e0566b4afd73c055"},"schema_version":"1.0"},"canonical_sha256":"334cd22d9952e8621ef7aad3be829a94dbc9b5029e775e1d71e2bb1eb002d1b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:47.987156Z","signature_b64":"DNsPgyPdzZ7QfsB9kETJFQBGpvvE/YFAFJaXBd0NbNkR07uS6ocXY1+D3xMV1EkyYULQkxx2rkL82bguYqKvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"334cd22d9952e8621ef7aad3be829a94dbc9b5029e775e1d71e2bb1eb002d1b8","last_reissued_at":"2026-07-05T09:25:47.986653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:47.986653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09187","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":"2026-07-05T09:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OslZq8NdnEDOkPj+cChuNm+/ROc98K58wJiTx2/jumIk8u4EjTQ/lZhgnHm2kjNT6pS/0tCG+mslxjMIGEHrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:17:22.764392Z"},"content_sha256":"021bb831b0e56b731c070b6dbbae29b9221d5edec2270d835ba8760c6d9b3781","schema_version":"1.0","event_id":"sha256:021bb831b0e56b731c070b6dbbae29b9221d5edec2270d835ba8760c6d9b3781"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GNGNELMZKLUGEHXXVLJ35AU2ST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Rewards via LLM-Generated Progress Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Brennan Shacklett, Christopher R\\'e, Kayvon Fatahalian, Kush Bhatia, Vishnu Sarukkai, Zander Majercik","submitted_at":"2024-10-11T18:41:15Z","abstract_excerpt":"Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. However, they often need many iterations of trial-and-error to generate effective reward functions. This process is costly because evaluating every sampled reward function requires completing the full policy optimization process for each function. In this paper, we introduce an LLM-driven reward generation framework that is able to produce state-of-the-art policies on the challenging Bi-DexHands benchmark with 20x fewer reward function samples than the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09187","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/2410.09187/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":"2026-07-05T09:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaGBdOYRfnp2OKTY/kOcKoHEWDSf+hHP+AtSGvC5WMzt1UCiICXhTzpUJYDI3nLFxXI9S7bLLyoInFCXbErzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:17:22.764882Z"},"content_sha256":"316a4480e829e70a4da16457fc18d0193ab47eeaa459a4d24e73ed5aa70d4eca","schema_version":"1.0","event_id":"sha256:316a4480e829e70a4da16457fc18d0193ab47eeaa459a4d24e73ed5aa70d4eca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/bundle.json","state_url":"https://pith.science/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/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":"2026-08-03T18:17:22Z","links":{"resolver":"https://pith.science/pith/GNGNELMZKLUGEHXXVLJ35AU2ST","bundle":"https://pith.science/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/bundle.json","state":"https://pith.science/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNGNELMZKLUGEHXXVLJ35AU2ST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GNGNELMZKLUGEHXXVLJ35AU2ST","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":"964780e1982c23220f37d049c80292db028eabf3d23cd768e0566b4afd73c055","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T18:41:15Z","title_canon_sha256":"332df6faa9b0535e1cadd4c75f6f894f12cb832220cb5fa98c60bbc822c082f0"},"schema_version":"1.0","source":{"id":"2410.09187","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09187","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09187v2","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09187","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"GNGNELMZKLUG","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"GNGNELMZKLUGEHXX","created_at":"2026-07-05T09:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"GNGNELMZ","created_at":"2026-07-05T09:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:316a4480e829e70a4da16457fc18d0193ab47eeaa459a4d24e73ed5aa70d4eca","target":"graph","created_at":"2026-07-05T09:25:47Z","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/2410.09187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. However, they often need many iterations of trial-and-error to generate effective reward functions. This process is costly because evaluating every sampled reward function requires completing the full policy optimization process for each function. In this paper, we introduce an LLM-driven reward generation framework that is able to produce state-of-the-art policies on the challenging Bi-DexHands benchmark with 20x fewer reward function samples than the","authors_text":"Brennan Shacklett, Christopher R\\'e, Kayvon Fatahalian, Kush Bhatia, Vishnu Sarukkai, Zander Majercik","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T18:41:15Z","title":"Automated Rewards via LLM-Generated Progress Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09187","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":"sha256:021bb831b0e56b731c070b6dbbae29b9221d5edec2270d835ba8760c6d9b3781","target":"record","created_at":"2026-07-05T09:25:47Z","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":"964780e1982c23220f37d049c80292db028eabf3d23cd768e0566b4afd73c055","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T18:41:15Z","title_canon_sha256":"332df6faa9b0535e1cadd4c75f6f894f12cb832220cb5fa98c60bbc822c082f0"},"schema_version":"1.0","source":{"id":"2410.09187","kind":"arxiv","version":2}},"canonical_sha256":"334cd22d9952e8621ef7aad3be829a94dbc9b5029e775e1d71e2bb1eb002d1b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"334cd22d9952e8621ef7aad3be829a94dbc9b5029e775e1d71e2bb1eb002d1b8","first_computed_at":"2026-07-05T09:25:47.986653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:47.986653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DNsPgyPdzZ7QfsB9kETJFQBGpvvE/YFAFJaXBd0NbNkR07uS6ocXY1+D3xMV1EkyYULQkxx2rkL82bguYqKvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:47.987156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09187","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:021bb831b0e56b731c070b6dbbae29b9221d5edec2270d835ba8760c6d9b3781","sha256:316a4480e829e70a4da16457fc18d0193ab47eeaa459a4d24e73ed5aa70d4eca"],"state_sha256":"4e755c129487aa227252f8831970fbbda9ca4d8d6a62be842889083d79eb9f99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUiQH3c9/WkJT7X1yu6YZ1bNWe0/eY4w3V8NU3/KXwrcHS57kvHw3DjBS2LoQcucb8AyfUvKAXHy7DdmaBkPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:17:22.768323Z","bundle_sha256":"52b6bbf2d7cb298cc9b10d8a530bdd483fab9a1d68c12072f9d4624090e60245"}}