{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GUC5CBYYSUXYTO4VQSNBWKWROS","short_pith_number":"pith:GUC5CBYY","canonical_record":{"source":{"id":"2606.23280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T12:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"18ac958a72b10302d462d72d7f8579bffd43ac6a41b335a2bb38411aa104992e","abstract_canon_sha256":"bc60d1f4f3c5d42b8794a25c134707aa8886c9fc3419b87f0c8de2b90be7b213"},"schema_version":"1.0"},"canonical_sha256":"3505d10718952f89bb95849a1b2ad174a34139d4893d8884e87aa85a8733f558","source":{"kind":"arxiv","id":"2606.23280","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23280","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23280v1","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23280","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_12","alias_value":"GUC5CBYYSUXY","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_16","alias_value":"GUC5CBYYSUXYTO4V","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_8","alias_value":"GUC5CBYY","created_at":"2026-06-23T03:14:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GUC5CBYYSUXYTO4VQSNBWKWROS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T12:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"18ac958a72b10302d462d72d7f8579bffd43ac6a41b335a2bb38411aa104992e","abstract_canon_sha256":"bc60d1f4f3c5d42b8794a25c134707aa8886c9fc3419b87f0c8de2b90be7b213"},"schema_version":"1.0"},"canonical_sha256":"3505d10718952f89bb95849a1b2ad174a34139d4893d8884e87aa85a8733f558","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:15.617805Z","signature_b64":"xBs+WGgvZSGZD+rpaUh3JfFd7hqJTFT7wUwKMsOVrFSGpPzV+ZaEGZte/++aqlBYiusijbRzL2ASXhQqHxGaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3505d10718952f89bb95849a1b2ad174a34139d4893d8884e87aa85a8733f558","last_reissued_at":"2026-06-23T03:14:15.617411Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:15.617411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23280","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":"2026-06-23T03:14:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r7OLcrCYrtvIKWXS3rTzFC/ijj0b50ikPGtQSJIQT5DQkKDFfFCequzIKcKNJQ/Bt66VAqteFLDJjAa8vq+5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:09:53.924167Z"},"content_sha256":"b9a5c019090eb12e00ebb3f053ed764ca137ab9753d0198f609d873a7c8af16d","schema_version":"1.0","event_id":"sha256:b9a5c019090eb12e00ebb3f053ed764ca137ab9753d0198f609d873a7c8af16d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GUC5CBYYSUXYTO4VQSNBWKWROS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haipeng Li, Kehu Yang, Miao Xin, Ning Yang, Xu Ding, Yang Yang, Yifan Zhang, Yuchuang Tong, Zhengtao Zhang","submitted_at":"2026-06-22T12:57:17Z","abstract_excerpt":"Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. However, existing approaches based on large language models (LLMs) remain inherently correlation-driven, relying on iterative environmental feedback to refine reward hypotheses for each specific task. This paradigm not only results in inefficient reasoning but also makes LLMs susceptible to semantically plausible yet causally spurious reward components, leading to ineffective optimization. To address these limitations, we propose the Causal Reward Wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23280","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/2606.23280/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":"2026-06-23T03:14:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NkqPQIRCVOdXkNlQSG9FAOJDhpUwxkvO5zS2BgFFF827DrScAKN/RthSyHtI8cp1EECuw7TPyoucRiDEPU2vDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:09:53.924548Z"},"content_sha256":"e46e2b31e9817e6a80c742f5bbe25207d128865058c53928d5cfb82d9e96be90","schema_version":"1.0","event_id":"sha256:e46e2b31e9817e6a80c742f5bbe25207d128865058c53928d5cfb82d9e96be90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/bundle.json","state_url":"https://pith.science/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/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":"2026-06-28T11:09:53Z","links":{"resolver":"https://pith.science/pith/GUC5CBYYSUXYTO4VQSNBWKWROS","bundle":"https://pith.science/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/bundle.json","state":"https://pith.science/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUC5CBYYSUXYTO4VQSNBWKWROS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUC5CBYYSUXYTO4VQSNBWKWROS","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":"bc60d1f4f3c5d42b8794a25c134707aa8886c9fc3419b87f0c8de2b90be7b213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T12:57:17Z","title_canon_sha256":"18ac958a72b10302d462d72d7f8579bffd43ac6a41b335a2bb38411aa104992e"},"schema_version":"1.0","source":{"id":"2606.23280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23280","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23280v1","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23280","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_12","alias_value":"GUC5CBYYSUXY","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_16","alias_value":"GUC5CBYYSUXYTO4V","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_8","alias_value":"GUC5CBYY","created_at":"2026-06-23T03:14:15Z"}],"graph_snapshots":[{"event_id":"sha256:e46e2b31e9817e6a80c742f5bbe25207d128865058c53928d5cfb82d9e96be90","target":"graph","created_at":"2026-06-23T03:14:15Z","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/2606.23280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. However, existing approaches based on large language models (LLMs) remain inherently correlation-driven, relying on iterative environmental feedback to refine reward hypotheses for each specific task. This paradigm not only results in inefficient reasoning but also makes LLMs susceptible to semantically plausible yet causally spurious reward components, leading to ineffective optimization. To address these limitations, we propose the Causal Reward Wo","authors_text":"Haipeng Li, Kehu Yang, Miao Xin, Ning Yang, Xu Ding, Yang Yang, Yifan Zhang, Yuchuang Tong, Zhengtao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T12:57:17Z","title":"Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23280","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:b9a5c019090eb12e00ebb3f053ed764ca137ab9753d0198f609d873a7c8af16d","target":"record","created_at":"2026-06-23T03:14:15Z","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":"bc60d1f4f3c5d42b8794a25c134707aa8886c9fc3419b87f0c8de2b90be7b213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T12:57:17Z","title_canon_sha256":"18ac958a72b10302d462d72d7f8579bffd43ac6a41b335a2bb38411aa104992e"},"schema_version":"1.0","source":{"id":"2606.23280","kind":"arxiv","version":1}},"canonical_sha256":"3505d10718952f89bb95849a1b2ad174a34139d4893d8884e87aa85a8733f558","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3505d10718952f89bb95849a1b2ad174a34139d4893d8884e87aa85a8733f558","first_computed_at":"2026-06-23T03:14:15.617411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:15.617411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xBs+WGgvZSGZD+rpaUh3JfFd7hqJTFT7wUwKMsOVrFSGpPzV+ZaEGZte/++aqlBYiusijbRzL2ASXhQqHxGaBg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:15.617805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9a5c019090eb12e00ebb3f053ed764ca137ab9753d0198f609d873a7c8af16d","sha256:e46e2b31e9817e6a80c742f5bbe25207d128865058c53928d5cfb82d9e96be90"],"state_sha256":"8c8cddd912daa24e1948b4cfe7bb1e6b980f6f451c5572fe64690a384e902050"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s762b2yqt3FdzlMFMLH70H35bRiO1A+DuCLvbKD2On7Zi7xYXJZrogLn/A0FBQm3S6z2IavnTrHRBhhhko04Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:09:53.926536Z","bundle_sha256":"9940d9f12c3a97af8b06b42df9c41254f4dba7b44bdb58ce03ed5e4a7e939728"}}