{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HF725U3HXKD34XXYO7EDOHIAAL","short_pith_number":"pith:HF725U3H","canonical_record":{"source":{"id":"2608.08491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T05:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"c6a01679ff2cda5ade8129f3fa80250e5a2990149a28e730aa5a5ab67e6159ad","abstract_canon_sha256":"6ea12cc26d71f23bf78463dd9c2c0d2c155ddf92cdbda62113863dde17e0acff"},"schema_version":"1.0"},"canonical_sha256":"397faed367ba87be5ef877c8371d0002e5b34d300f4229ad158e324ecb91d517","source":{"kind":"arxiv","id":"2608.08491","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08491","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08491v1","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08491","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"HF725U3HXKD3","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"HF725U3HXKD34XXY","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"HF725U3H","created_at":"2026-08-11T01:22:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HF725U3HXKD34XXYO7EDOHIAAL","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T05:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"c6a01679ff2cda5ade8129f3fa80250e5a2990149a28e730aa5a5ab67e6159ad","abstract_canon_sha256":"6ea12cc26d71f23bf78463dd9c2c0d2c155ddf92cdbda62113863dde17e0acff"},"schema_version":"1.0"},"canonical_sha256":"397faed367ba87be5ef877c8371d0002e5b34d300f4229ad158e324ecb91d517","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:46.823903Z","signature_b64":"nJKIbzbq+hPYBg5LiRy1K5XNbXLDHcK4jFPPo9AyPPGhDKKVby4QEj7+J70StLRDbwsgpbud4DvAbQuvQFIADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"397faed367ba87be5ef877c8371d0002e5b34d300f4229ad158e324ecb91d517","last_reissued_at":"2026-08-11T01:22:46.821466Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:46.821466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08491","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":"2026-08-11T01:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgq8ZGCnfmGTNt1JGZq8hGviS969JtqokPj4/TtVh5ZGpSj/rHVc2weieRYf5T7HbfLqlbbs2RZdt38D8ZSWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:04:21.304534Z"},"content_sha256":"6200b18f530d1b8719294b3dddbe64ebb67aa612328ebc421029a9496dbb6a33","schema_version":"1.0","event_id":"sha256:6200b18f530d1b8719294b3dddbe64ebb67aa612328ebc421029a9496dbb6a33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HF725U3HXKD34XXYO7EDOHIAAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Liu, Bo Jia, Chenggang Xie, Hanchu Ni, Jiaxuan Zhu, Renzhao Liang, Shikun Zhang, Wei Ye, Xiaozhu Ju, Yan Zhan, Yidong Wang, Yiran Zhao, Yi Zhang, Yong Dai, Zhenyu Cui, Zhongkuan Mao, Zilei Yang, Ziteng Feng, Ziyi Zhou","submitted_at":"2026-08-09T05:25:22Z","abstract_excerpt":"Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08491","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/2608.08491/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":"2026-08-11T01:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lw5G63HWUD5iDLm6GGv71BGoHSr9MRYQtI5LwGPrnvFRN7PHSGsFXgsOyU3G1T3PHUTtfsykgWrcHgZ4PO/+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:04:21.305470Z"},"content_sha256":"db39074d1e8fd43f7abb5204cbd87d153629524ca643109d13c7444a7bb418d9","schema_version":"1.0","event_id":"sha256:db39074d1e8fd43f7abb5204cbd87d153629524ca643109d13c7444a7bb418d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HF725U3HXKD34XXYO7EDOHIAAL/bundle.json","state_url":"https://pith.science/pith/HF725U3HXKD34XXYO7EDOHIAAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HF725U3HXKD34XXYO7EDOHIAAL/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":"2026-08-18T18:04:21Z","links":{"resolver":"https://pith.science/pith/HF725U3HXKD34XXYO7EDOHIAAL","bundle":"https://pith.science/pith/HF725U3HXKD34XXYO7EDOHIAAL/bundle.json","state":"https://pith.science/pith/HF725U3HXKD34XXYO7EDOHIAAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HF725U3HXKD34XXYO7EDOHIAAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HF725U3HXKD34XXYO7EDOHIAAL","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":"6ea12cc26d71f23bf78463dd9c2c0d2c155ddf92cdbda62113863dde17e0acff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T05:25:22Z","title_canon_sha256":"c6a01679ff2cda5ade8129f3fa80250e5a2990149a28e730aa5a5ab67e6159ad"},"schema_version":"1.0","source":{"id":"2608.08491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08491","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08491v1","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08491","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"HF725U3HXKD3","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"HF725U3HXKD34XXY","created_at":"2026-08-11T01:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"HF725U3H","created_at":"2026-08-11T01:22:46Z"}],"graph_snapshots":[{"event_id":"sha256:db39074d1e8fd43f7abb5204cbd87d153629524ca643109d13c7444a7bb418d9","target":"graph","created_at":"2026-08-11T01:22:46Z","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/2608.08491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise an","authors_text":"Biao Liu, Bo Jia, Chenggang Xie, Hanchu Ni, Jiaxuan Zhu, Renzhao Liang, Shikun Zhang, Wei Ye, Xiaozhu Ju, Yan Zhan, Yidong Wang, Yiran Zhao, Yi Zhang, Yong Dai, Zhenyu Cui, Zhongkuan Mao, Zilei Yang, Ziteng Feng, Ziyi Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T05:25:22Z","title":"TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08491","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":"sha256:6200b18f530d1b8719294b3dddbe64ebb67aa612328ebc421029a9496dbb6a33","target":"record","created_at":"2026-08-11T01:22:46Z","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":"6ea12cc26d71f23bf78463dd9c2c0d2c155ddf92cdbda62113863dde17e0acff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T05:25:22Z","title_canon_sha256":"c6a01679ff2cda5ade8129f3fa80250e5a2990149a28e730aa5a5ab67e6159ad"},"schema_version":"1.0","source":{"id":"2608.08491","kind":"arxiv","version":1}},"canonical_sha256":"397faed367ba87be5ef877c8371d0002e5b34d300f4229ad158e324ecb91d517","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"397faed367ba87be5ef877c8371d0002e5b34d300f4229ad158e324ecb91d517","first_computed_at":"2026-08-11T01:22:46.821466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:46.821466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nJKIbzbq+hPYBg5LiRy1K5XNbXLDHcK4jFPPo9AyPPGhDKKVby4QEj7+J70StLRDbwsgpbud4DvAbQuvQFIADQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:46.823903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6200b18f530d1b8719294b3dddbe64ebb67aa612328ebc421029a9496dbb6a33","sha256:db39074d1e8fd43f7abb5204cbd87d153629524ca643109d13c7444a7bb418d9"],"state_sha256":"114ab7677b30b4622e40a8b6d372fc2dc8bc38d8fbee2dab5fcc7c8ebd72c6b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNUJflJwxGCfDflTTvtrpREI2sykALK/95OfPwEFyv93TiFdHGpDj6zhYdWngYiCDq3Qtix8yS6Z3QDOnxGzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:04:21.312340Z","bundle_sha256":"67f5425a59f93743b68315caf74ece284a71eb10ab9e647ca0befb3527561abb"}}