{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3ULHN3X4P3KAC7AJHUW4TNEESN","short_pith_number":"pith:3ULHN3X4","canonical_record":{"source":{"id":"2605.19259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-19T02:10:04Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"39ec59aa3779be2f84a7bbeb8c585ed39a1a15f6613bf8944746cda0657d26fe","abstract_canon_sha256":"696d463f4330763d4748fb109bf6c04cb07337526df3c40306ddbdb84d25970d"},"schema_version":"1.0"},"canonical_sha256":"dd1676eefc7ed4017c093d2dc9b48493625a24b3546204b8360432d251df0798","source":{"kind":"arxiv","id":"2605.19259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19259","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19259v1","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19259","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"3ULHN3X4P3KA","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"3ULHN3X4P3KAC7AJ","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"3ULHN3X4","created_at":"2026-05-20T01:05:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3ULHN3X4P3KAC7AJHUW4TNEESN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-19T02:10:04Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"39ec59aa3779be2f84a7bbeb8c585ed39a1a15f6613bf8944746cda0657d26fe","abstract_canon_sha256":"696d463f4330763d4748fb109bf6c04cb07337526df3c40306ddbdb84d25970d"},"schema_version":"1.0"},"canonical_sha256":"dd1676eefc7ed4017c093d2dc9b48493625a24b3546204b8360432d251df0798","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:36.377189Z","signature_b64":"QORbsx0WWPOJI8uY3VZJt+XptEBr9cCxTkQp/pSOSklvX+dUt1jhdaTSzZPzwjzrSykV0omTEEDN0gn4O7tsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd1676eefc7ed4017c093d2dc9b48493625a24b3546204b8360432d251df0798","last_reissued_at":"2026-05-20T01:05:36.376581Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:36.376581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19259","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":"2026-05-20T01:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfD5dHV0wn9GSSDnSOgzjje1MLXCLLm6Ofcxpb+f9TeUOQAFQ7bnXloNmvboyEzXG1m+9Xx7KBu58vDpOPg2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:47:17.280441Z"},"content_sha256":"c6c726143b26c7d2d724ef119fd1cfab724ac2e68b1ec957aedde7169ea840a7","schema_version":"1.0","event_id":"sha256:c6c726143b26c7d2d724ef119fd1cfab724ac2e68b1ec957aedde7169ea840a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3ULHN3X4P3KAC7AJHUW4TNEESN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Guanwen Xie, Jingzehua Xu, Shuai Zhang, Yimian Ding, Yiyuan Yang","submitted_at":"2026-05-19T02:10:04Z","abstract_excerpt":"We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective learning-based methods (LB). ERFSL generates reward components based on explicit user requirements, rectifies them using a reward critic, and iteratively optimizes the weights of these components based on textual context generated by the training log analyzer. Applied to a simulation-based benchmark task, the reward critic corrects reward codes with only one feedback iteration per requirement, and the reward weight initializer acquires diverse reward functions with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19259","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/2605.19259/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":"2026-05-20T01:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PpxxdYpNBiEpeade4qtjZ9KuQtzUQhoAlHloEO6LpWjt19M+bpnezs4R0AbYvAWZSiBAqXAShVMf4DWtLo9mDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:47:17.281546Z"},"content_sha256":"c2bb7b9c1ef04afaf80e14db9ed78d6967b278484633a331048c64ea83bec5e9","schema_version":"1.0","event_id":"sha256:c2bb7b9c1ef04afaf80e14db9ed78d6967b278484633a331048c64ea83bec5e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/bundle.json","state_url":"https://pith.science/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/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":"2026-05-26T19:47:17Z","links":{"resolver":"https://pith.science/pith/3ULHN3X4P3KAC7AJHUW4TNEESN","bundle":"https://pith.science/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/bundle.json","state":"https://pith.science/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ULHN3X4P3KAC7AJHUW4TNEESN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3ULHN3X4P3KAC7AJHUW4TNEESN","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":"696d463f4330763d4748fb109bf6c04cb07337526df3c40306ddbdb84d25970d","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-19T02:10:04Z","title_canon_sha256":"39ec59aa3779be2f84a7bbeb8c585ed39a1a15f6613bf8944746cda0657d26fe"},"schema_version":"1.0","source":{"id":"2605.19259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19259","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19259v1","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19259","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"3ULHN3X4P3KA","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"3ULHN3X4P3KAC7AJ","created_at":"2026-05-20T01:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"3ULHN3X4","created_at":"2026-05-20T01:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:c2bb7b9c1ef04afaf80e14db9ed78d6967b278484633a331048c64ea83bec5e9","target":"graph","created_at":"2026-05-20T01:05:36Z","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/2605.19259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective learning-based methods (LB). ERFSL generates reward components based on explicit user requirements, rectifies them using a reward critic, and iteratively optimizes the weights of these components based on textual context generated by the training log analyzer. Applied to a simulation-based benchmark task, the reward critic corrects reward codes with only one feedback iteration per requirement, and the reward weight initializer acquires diverse reward functions with","authors_text":"Guanwen Xie, Jingzehua Xu, Shuai Zhang, Yimian Ding, Yiyuan Yang","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-19T02:10:04Z","title":"ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19259","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:c6c726143b26c7d2d724ef119fd1cfab724ac2e68b1ec957aedde7169ea840a7","target":"record","created_at":"2026-05-20T01:05:36Z","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":"696d463f4330763d4748fb109bf6c04cb07337526df3c40306ddbdb84d25970d","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-19T02:10:04Z","title_canon_sha256":"39ec59aa3779be2f84a7bbeb8c585ed39a1a15f6613bf8944746cda0657d26fe"},"schema_version":"1.0","source":{"id":"2605.19259","kind":"arxiv","version":1}},"canonical_sha256":"dd1676eefc7ed4017c093d2dc9b48493625a24b3546204b8360432d251df0798","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd1676eefc7ed4017c093d2dc9b48493625a24b3546204b8360432d251df0798","first_computed_at":"2026-05-20T01:05:36.376581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:36.376581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QORbsx0WWPOJI8uY3VZJt+XptEBr9cCxTkQp/pSOSklvX+dUt1jhdaTSzZPzwjzrSykV0omTEEDN0gn4O7tsAw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:36.377189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6c726143b26c7d2d724ef119fd1cfab724ac2e68b1ec957aedde7169ea840a7","sha256:c2bb7b9c1ef04afaf80e14db9ed78d6967b278484633a331048c64ea83bec5e9"],"state_sha256":"3c449ca196495e53a935747897103e0f722d047773ec7ae1df40b6a2982a3184"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pp0ap0TPX7VU12OKAfgin/b2ClJZYsfbUme6SsEqaG7xVRv8XxlvAPsa4ZF/wlKvl47fb0wIH8/hoOLSzgkLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:47:17.284852Z","bundle_sha256":"b1855d865ee1ec7037dd249acb758483d3b70072d5826970cc4de7f4f21b5c46"}}