{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JOK6TUPJEIWHVFXJLX6KZAMXQT","short_pith_number":"pith:JOK6TUPJ","canonical_record":{"source":{"id":"2507.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T03:09:17Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"63f16b25ccb45e8f6e3f7ad5b9dafb8858feb1ac88b3441567e8d6e21b1aeaff","abstract_canon_sha256":"7baa668a7fb7b4a26d36458f07b16ebfd23ba1a7728611fe1b5d92eb1e0e0b7b"},"schema_version":"1.0"},"canonical_sha256":"4b95e9d1e9222c7a96e95dfcac819784da1ecf22f5c90b3b5af58658ed89dae8","source":{"kind":"arxiv","id":"2507.02256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02256","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02256v1","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02256","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"JOK6TUPJEIWH","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"JOK6TUPJEIWHVFXJ","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"JOK6TUPJ","created_at":"2026-07-05T11:31:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JOK6TUPJEIWHVFXJLX6KZAMXQT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T03:09:17Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"63f16b25ccb45e8f6e3f7ad5b9dafb8858feb1ac88b3441567e8d6e21b1aeaff","abstract_canon_sha256":"7baa668a7fb7b4a26d36458f07b16ebfd23ba1a7728611fe1b5d92eb1e0e0b7b"},"schema_version":"1.0"},"canonical_sha256":"4b95e9d1e9222c7a96e95dfcac819784da1ecf22f5c90b3b5af58658ed89dae8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:14.628346Z","signature_b64":"1eIC4HarmtF+qchaVuQXeK14n93EI3uD/74FZC5WdrIcrdKh2RlbOUMN5tOrdLKEmn5w6oo1fkMuiIjkwbQnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b95e9d1e9222c7a96e95dfcac819784da1ecf22f5c90b3b5af58658ed89dae8","last_reissued_at":"2026-07-05T11:31:14.627853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:14.627853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.02256","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":"2026-07-05T11:31:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mhg3KaR9W2NZYua/LRjlEMXaCTU/+6g8POcAjiDLcKTn3RQKDn7UpYjluuxeYH1OsePJBjPOUGmKdvKCnX4GBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:12:44.300047Z"},"content_sha256":"c3b7d2ce36a79212ed1b086810c09056e5a60ac6f07db91ef8d1b169dfeab6bf","schema_version":"1.0","event_id":"sha256:c3b7d2ce36a79212ed1b086810c09056e5a60ac6f07db91ef8d1b169dfeab6bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JOK6TUPJEIWHVFXJLX6KZAMXQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-aware Reward Design Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bosong Ding, Miao Xin, Xiaolu Zhou, Yang Yang","submitted_at":"2025-07-03T03:09:17Z","abstract_excerpt":"Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent advances have explored leveraging large language models (LLMs) to automate reward function design. However, their suboptimal performance in numerical optimization often yields unsatisfactory reward quality, while the evolutionary search paradigm demonstrates inefficient utilization of simulation resources, resulting in prohibitively lengthy design cycles with dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02256","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/2507.02256/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":"2026-07-05T11:31:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQTtiIRH+dSdFJSQSI7BjaaPnpk4TpxlFyTMJ/j/7wkSKpNDg1hRNYhBQt62SVym9YmqSABDk43QbTnqi90cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:12:44.300554Z"},"content_sha256":"8bf1746f52765bc1dd9eb949946075a566b18da05146abed707a609b059e76ec","schema_version":"1.0","event_id":"sha256:8bf1746f52765bc1dd9eb949946075a566b18da05146abed707a609b059e76ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/bundle.json","state_url":"https://pith.science/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/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":"2026-08-15T07:12:44Z","links":{"resolver":"https://pith.science/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT","bundle":"https://pith.science/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/bundle.json","state":"https://pith.science/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOK6TUPJEIWHVFXJLX6KZAMXQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JOK6TUPJEIWHVFXJLX6KZAMXQT","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":"7baa668a7fb7b4a26d36458f07b16ebfd23ba1a7728611fe1b5d92eb1e0e0b7b","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T03:09:17Z","title_canon_sha256":"63f16b25ccb45e8f6e3f7ad5b9dafb8858feb1ac88b3441567e8d6e21b1aeaff"},"schema_version":"1.0","source":{"id":"2507.02256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02256","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02256v1","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02256","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"JOK6TUPJEIWH","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"JOK6TUPJEIWHVFXJ","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"JOK6TUPJ","created_at":"2026-07-05T11:31:14Z"}],"graph_snapshots":[{"event_id":"sha256:8bf1746f52765bc1dd9eb949946075a566b18da05146abed707a609b059e76ec","target":"graph","created_at":"2026-07-05T11:31:14Z","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/2507.02256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent advances have explored leveraging large language models (LLMs) to automate reward function design. However, their suboptimal performance in numerical optimization often yields unsatisfactory reward quality, while the evolutionary search paradigm demonstrates inefficient utilization of simulation resources, resulting in prohibitively lengthy design cycles with dis","authors_text":"Bosong Ding, Miao Xin, Xiaolu Zhou, Yang Yang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T03:09:17Z","title":"Uncertainty-aware Reward Design Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02256","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:c3b7d2ce36a79212ed1b086810c09056e5a60ac6f07db91ef8d1b169dfeab6bf","target":"record","created_at":"2026-07-05T11:31:14Z","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":"7baa668a7fb7b4a26d36458f07b16ebfd23ba1a7728611fe1b5d92eb1e0e0b7b","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T03:09:17Z","title_canon_sha256":"63f16b25ccb45e8f6e3f7ad5b9dafb8858feb1ac88b3441567e8d6e21b1aeaff"},"schema_version":"1.0","source":{"id":"2507.02256","kind":"arxiv","version":1}},"canonical_sha256":"4b95e9d1e9222c7a96e95dfcac819784da1ecf22f5c90b3b5af58658ed89dae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b95e9d1e9222c7a96e95dfcac819784da1ecf22f5c90b3b5af58658ed89dae8","first_computed_at":"2026-07-05T11:31:14.627853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:14.627853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1eIC4HarmtF+qchaVuQXeK14n93EI3uD/74FZC5WdrIcrdKh2RlbOUMN5tOrdLKEmn5w6oo1fkMuiIjkwbQnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:14.628346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3b7d2ce36a79212ed1b086810c09056e5a60ac6f07db91ef8d1b169dfeab6bf","sha256:8bf1746f52765bc1dd9eb949946075a566b18da05146abed707a609b059e76ec"],"state_sha256":"7c3c4392ffc35e669e43c4ac57db4fa0e554cf6aa73ab20d8297cd7b43db7578"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QELNdxG0nAZtHGr3qoxmEesbdvIvt71vP/M7NffMEK2G2HWBtGAnDWBf/oJs+TSnGfKV5PRVKG4EmEfJ5ANnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T07:12:44.305523Z","bundle_sha256":"60733baa9e8a241db8fb5339ff402eab06919382bd5411c56119ccc8fdc4b454"}}