{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3EQHYAA67A54YF5NCAZJTQAWVV","short_pith_number":"pith:3EQHYAA6","canonical_record":{"source":{"id":"2406.01309","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-03T13:23:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a6e29ed6f6dc27a0f937d1badccb1c35dc264084c942ed754dbb8295e6a74a1","abstract_canon_sha256":"c5839cbaddfdbb5f0c1c4d8c72bed4ad35fd93b641228867019287001a663efd"},"schema_version":"1.0"},"canonical_sha256":"d9207c001ef83bcc17ad103299c016ad7dae3ab1ad11d8add8805a216b3f88af","source":{"kind":"arxiv","id":"2406.01309","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01309","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01309v4","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01309","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"3EQHYAA67A54","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"3EQHYAA67A54YF5N","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"3EQHYAA6","created_at":"2026-07-05T11:07:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3EQHYAA67A54YF5NCAZJTQAWVV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01309","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-03T13:23:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a6e29ed6f6dc27a0f937d1badccb1c35dc264084c942ed754dbb8295e6a74a1","abstract_canon_sha256":"c5839cbaddfdbb5f0c1c4d8c72bed4ad35fd93b641228867019287001a663efd"},"schema_version":"1.0"},"canonical_sha256":"d9207c001ef83bcc17ad103299c016ad7dae3ab1ad11d8add8805a216b3f88af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:57.778223Z","signature_b64":"8QWLIYRpEDUgE2zeDP0+DzqGW+F3CK0inyTWZBKihtNsrJ7+YBLNoTajESTql6hmpARGPcq1+aJN28UHWMWlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9207c001ef83bcc17ad103299c016ad7dae3ab1ad11d8add8805a216b3f88af","last_reissued_at":"2026-07-05T11:07:57.777678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:57.777678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01309","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Jb8LJkMzs0fNPriJ2H3j3BzUi+LgyqGslpExfsmCsiS5krSb+BMYCoGx+JhRI25iFOA1Swnls0ySzbhz8FHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:25:14.510433Z"},"content_sha256":"5aefbd58e961bfd5e84549c71358fa693716e7e764539c6417a8a099bb6a7199","schema_version":"1.0","event_id":"sha256:5aefbd58e961bfd5e84549c71358fa693716e7e764539c6417a8a099bb6a7199"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3EQHYAA67A54YF5NCAZJTQAWVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Alkis Sygkounas, Amy Loutfi, Andreas Persson, Pedro Zuidberg Dos Martires, Rishi Hazra","submitted_at":"2024-06-03T13:23:27Z","abstract_excerpt":"Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify explicitly. In recent works, large language models (LLMs) have been used for reward generation from natural language task descriptions, leveraging their extensive instruction tuning and commonsense understanding of human behavior. In this work, we hypothesize that LLMs, guided by human feedback, can be used to formulate reward functions that reflect human implicit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01309","kind":"arxiv","version":4},"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/2406.01309/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":"2026-07-05T11:07:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rMlK73rgT7008tCbYXnA7ZqkRiLPmGNlIdOnT71Ebo4HTN66CuN1PqATOcQHnmFmtnuJnVU7MqWtMh2+SpwMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:25:14.511321Z"},"content_sha256":"3ecf38fe0ad17f139f9399efe92704877b1874e3e7b8e2b5db0a8a17a1a282fa","schema_version":"1.0","event_id":"sha256:3ecf38fe0ad17f139f9399efe92704877b1874e3e7b8e2b5db0a8a17a1a282fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EQHYAA67A54YF5NCAZJTQAWVV/bundle.json","state_url":"https://pith.science/pith/3EQHYAA67A54YF5NCAZJTQAWVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EQHYAA67A54YF5NCAZJTQAWVV/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":"2026-08-21T21:25:14Z","links":{"resolver":"https://pith.science/pith/3EQHYAA67A54YF5NCAZJTQAWVV","bundle":"https://pith.science/pith/3EQHYAA67A54YF5NCAZJTQAWVV/bundle.json","state":"https://pith.science/pith/3EQHYAA67A54YF5NCAZJTQAWVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EQHYAA67A54YF5NCAZJTQAWVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3EQHYAA67A54YF5NCAZJTQAWVV","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":"c5839cbaddfdbb5f0c1c4d8c72bed4ad35fd93b641228867019287001a663efd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-03T13:23:27Z","title_canon_sha256":"8a6e29ed6f6dc27a0f937d1badccb1c35dc264084c942ed754dbb8295e6a74a1"},"schema_version":"1.0","source":{"id":"2406.01309","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01309","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01309v4","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01309","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"3EQHYAA67A54","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"3EQHYAA67A54YF5N","created_at":"2026-07-05T11:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"3EQHYAA6","created_at":"2026-07-05T11:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:3ecf38fe0ad17f139f9399efe92704877b1874e3e7b8e2b5db0a8a17a1a282fa","target":"graph","created_at":"2026-07-05T11:07:57Z","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/2406.01309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify explicitly. In recent works, large language models (LLMs) have been used for reward generation from natural language task descriptions, leveraging their extensive instruction tuning and commonsense understanding of human behavior. In this work, we hypothesize that LLMs, guided by human feedback, can be used to formulate reward functions that reflect human implicit","authors_text":"Alkis Sygkounas, Amy Loutfi, Andreas Persson, Pedro Zuidberg Dos Martires, Rishi Hazra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-03T13:23:27Z","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01309","kind":"arxiv","version":4},"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":"sha256:5aefbd58e961bfd5e84549c71358fa693716e7e764539c6417a8a099bb6a7199","target":"record","created_at":"2026-07-05T11:07:57Z","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":"c5839cbaddfdbb5f0c1c4d8c72bed4ad35fd93b641228867019287001a663efd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-06-03T13:23:27Z","title_canon_sha256":"8a6e29ed6f6dc27a0f937d1badccb1c35dc264084c942ed754dbb8295e6a74a1"},"schema_version":"1.0","source":{"id":"2406.01309","kind":"arxiv","version":4}},"canonical_sha256":"d9207c001ef83bcc17ad103299c016ad7dae3ab1ad11d8add8805a216b3f88af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9207c001ef83bcc17ad103299c016ad7dae3ab1ad11d8add8805a216b3f88af","first_computed_at":"2026-07-05T11:07:57.777678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:57.777678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8QWLIYRpEDUgE2zeDP0+DzqGW+F3CK0inyTWZBKihtNsrJ7+YBLNoTajESTql6hmpARGPcq1+aJN28UHWMWlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:57.778223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01309","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aefbd58e961bfd5e84549c71358fa693716e7e764539c6417a8a099bb6a7199","sha256:3ecf38fe0ad17f139f9399efe92704877b1874e3e7b8e2b5db0a8a17a1a282fa"],"state_sha256":"950ca26ce00105e78d70dc54efe0e8cb69305fc7fc98c706d41b14d01632ab24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8cM34hbO7dAEQQrMWfYQaFNenNOccb5mt6qnsqmLaPgLersxZ84vJ7yUAM5fwxNtKE2d/dpsocltQOc4CZlDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:25:14.516922Z","bundle_sha256":"5ba3e80487149541b263546f5acf8ee13cd4b65552179a7996dd9bccc3a04a1d"}}