{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7JCSZ32N4NAUAJA2JSQEH44AUI","short_pith_number":"pith:7JCSZ32N","canonical_record":{"source":{"id":"2504.07596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T09:48:56Z","cross_cats_sorted":[],"title_canon_sha256":"a4366d64e4c5987e95b19e1be8365c2507d7e1bde5cdc0505780b201beda2409","abstract_canon_sha256":"0fa17b5f9f7dda4ee3f00a2e04c7706114006a3a61a6757ac859997c9456d36c"},"schema_version":"1.0"},"canonical_sha256":"fa452cef4de34140241a4ca043f380a220317a3c7c7e8cde6233fb97f24bc564","source":{"kind":"arxiv","id":"2504.07596","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07596","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07596v2","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07596","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"7JCSZ32N4NAU","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"7JCSZ32N4NAUAJA2","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"7JCSZ32N","created_at":"2026-07-05T10:47:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7JCSZ32N4NAUAJA2JSQEH44AUI","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T09:48:56Z","cross_cats_sorted":[],"title_canon_sha256":"a4366d64e4c5987e95b19e1be8365c2507d7e1bde5cdc0505780b201beda2409","abstract_canon_sha256":"0fa17b5f9f7dda4ee3f00a2e04c7706114006a3a61a6757ac859997c9456d36c"},"schema_version":"1.0"},"canonical_sha256":"fa452cef4de34140241a4ca043f380a220317a3c7c7e8cde6233fb97f24bc564","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:39.882506Z","signature_b64":"p+1FEOMG+V6qruCApIDNd6dbMnvKqcTzzYjgwMUYIm/EI749lv6tC3/eFcB0L3C3HPSrcbiSNuEPgu2oeJwSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa452cef4de34140241a4ca043f380a220317a3c7c7e8cde6233fb97f24bc564","last_reissued_at":"2026-07-05T10:47:39.882014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:39.882014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07596","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":"2026-07-05T10:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxminSU3dB3w7xsDO1rN1/efbSyGW0Y1nRff1Li+wYPBfZs8Ngw+G8cKqYLX2lKoQTS9xXUo46prtsonr6ryCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:27:02.693198Z"},"content_sha256":"3033e468cc0fbe270feefbb9079e6ac000f3cabd8d209bc354cb09e82ab0994f","schema_version":"1.0","event_id":"sha256:3033e468cc0fbe270feefbb9079e6ac000f3cabd8d209bc354cb09e82ab0994f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7JCSZ32N4NAUAJA2JSQEH44AUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Dong, Mingdong Wu, Tianhao Wu, Yangang Wang, Yuanfei Wang, Zen Kit Heng, Zimeng Zhao","submitted_at":"2025-04-10T09:48:56Z","abstract_excerpt":"Large Language Models (LLMs) are emerging as promising tools for automated reinforcement learning (RL) reward design, owing to their robust capabilities in commonsense reasoning and code generation. By engaging in dialogues with RL agents, LLMs construct a Reward Observation Space (ROS) by selecting relevant environment states and defining their internal operations. However, existing frameworks have not effectively leveraged historical exploration data or manual task descriptions to iteratively evolve this space. In this paper, we propose a novel heuristic framework that enhances LLM-driven re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07596","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/2504.07596/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":"2026-07-05T10:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wKX5NzFmVDutfERdKeWAEL2Qm65lSn5/o0DGFEg+LzFz1CSpfojuOUgLvAvr6M257lI7GSdKCzvkQmIaQylDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:27:02.693586Z"},"content_sha256":"e06e4b058da1564a4947cce287cd90bdbcba738030f23ce13ff42e9147f7f592","schema_version":"1.0","event_id":"sha256:e06e4b058da1564a4947cce287cd90bdbcba738030f23ce13ff42e9147f7f592"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/bundle.json","state_url":"https://pith.science/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/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":"2026-07-06T12:27:02Z","links":{"resolver":"https://pith.science/pith/7JCSZ32N4NAUAJA2JSQEH44AUI","bundle":"https://pith.science/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/bundle.json","state":"https://pith.science/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JCSZ32N4NAUAJA2JSQEH44AUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7JCSZ32N4NAUAJA2JSQEH44AUI","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":"0fa17b5f9f7dda4ee3f00a2e04c7706114006a3a61a6757ac859997c9456d36c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T09:48:56Z","title_canon_sha256":"a4366d64e4c5987e95b19e1be8365c2507d7e1bde5cdc0505780b201beda2409"},"schema_version":"1.0","source":{"id":"2504.07596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07596","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07596v2","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07596","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"7JCSZ32N4NAU","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"7JCSZ32N4NAUAJA2","created_at":"2026-07-05T10:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"7JCSZ32N","created_at":"2026-07-05T10:47:39Z"}],"graph_snapshots":[{"event_id":"sha256:e06e4b058da1564a4947cce287cd90bdbcba738030f23ce13ff42e9147f7f592","target":"graph","created_at":"2026-07-05T10:47:39Z","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/2504.07596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are emerging as promising tools for automated reinforcement learning (RL) reward design, owing to their robust capabilities in commonsense reasoning and code generation. By engaging in dialogues with RL agents, LLMs construct a Reward Observation Space (ROS) by selecting relevant environment states and defining their internal operations. However, existing frameworks have not effectively leveraged historical exploration data or manual task descriptions to iteratively evolve this space. In this paper, we propose a novel heuristic framework that enhances LLM-driven re","authors_text":"Hao Dong, Mingdong Wu, Tianhao Wu, Yangang Wang, Yuanfei Wang, Zen Kit Heng, Zimeng Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T09:48:56Z","title":"Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07596","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":"sha256:3033e468cc0fbe270feefbb9079e6ac000f3cabd8d209bc354cb09e82ab0994f","target":"record","created_at":"2026-07-05T10:47:39Z","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":"0fa17b5f9f7dda4ee3f00a2e04c7706114006a3a61a6757ac859997c9456d36c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-10T09:48:56Z","title_canon_sha256":"a4366d64e4c5987e95b19e1be8365c2507d7e1bde5cdc0505780b201beda2409"},"schema_version":"1.0","source":{"id":"2504.07596","kind":"arxiv","version":2}},"canonical_sha256":"fa452cef4de34140241a4ca043f380a220317a3c7c7e8cde6233fb97f24bc564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa452cef4de34140241a4ca043f380a220317a3c7c7e8cde6233fb97f24bc564","first_computed_at":"2026-07-05T10:47:39.882014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:39.882014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p+1FEOMG+V6qruCApIDNd6dbMnvKqcTzzYjgwMUYIm/EI749lv6tC3/eFcB0L3C3HPSrcbiSNuEPgu2oeJwSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:39.882506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3033e468cc0fbe270feefbb9079e6ac000f3cabd8d209bc354cb09e82ab0994f","sha256:e06e4b058da1564a4947cce287cd90bdbcba738030f23ce13ff42e9147f7f592"],"state_sha256":"db268c8bda79f5bf002ede77001297dbcd3ee17beb2783ba5fa219a5357ae5ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwZuovUUohDIS05PDsKqixzIKQf5qi2Fle4kAnCql1UbJaDNmTMIqoqdGgXYAvVHrogi6KdHiubJN9QW7u96CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:27:02.695556Z","bundle_sha256":"a8bac739b7efd2f7c7dbcb49285bc15477720daf5835f4a9df5ddd59b86bcbc5"}}