{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WAOZHUPQAPAK4XSKEVCXUTHGLV","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":"0d259162feb71520dc6a58693725245aedc9de24ead405414e98a6a8f3eb68f7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-09T14:22:43Z","title_canon_sha256":"c6562357fe48dbcdacf6967ac17b694e819b7d097387e3a8e9a0845dd0335203"},"schema_version":"1.0","source":{"id":"2505.06079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06079","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06079v1","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06079","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"WAOZHUPQAPAK","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"WAOZHUPQAPAK4XSK","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"WAOZHUPQ","created_at":"2026-07-05T11:00:53Z"}],"graph_snapshots":[{"event_id":"sha256:4cf72ed7418a31c683eb0ccdf66475f5558b190a4514d53e8e607b44b93b7cd8","target":"graph","created_at":"2026-07-05T11:00:53Z","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/2505.06079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference feedback collected by human or VLM annotators is often noisy, presenting a significant challenge for preference-based reinforcement learning that relies on accurate preference labels. To address this challenge, we propose TREND, a novel framework that integrates few-shot expert demonstrations with a tri-teaching strategy for effective noise mitigation. Our method trains three reward models simultaneously, where each model views its small-loss preference pairs as useful knowledge and teaches such useful pairs to its peer network for updating the parameters. Remarkably, our approach r","authors_text":"Abhinav Shrivastava, Anubhav Gupta, Daniel Ekpo, Mara Levy, Ruijie Zheng, Shuaiyi Huang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-09T14:22:43Z","title":"TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06079","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":"sha256:2a903cb908f0bd7f9789eeab998a81f4519d1f09fd2070861d19e1ae8168bf69","target":"record","created_at":"2026-07-05T11:00:53Z","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":"0d259162feb71520dc6a58693725245aedc9de24ead405414e98a6a8f3eb68f7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-09T14:22:43Z","title_canon_sha256":"c6562357fe48dbcdacf6967ac17b694e819b7d097387e3a8e9a0845dd0335203"},"schema_version":"1.0","source":{"id":"2505.06079","kind":"arxiv","version":1}},"canonical_sha256":"b01d93d1f003c0ae5e4a25457a4ce65d4f6aceec2b43a9931f5827516673123f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b01d93d1f003c0ae5e4a25457a4ce65d4f6aceec2b43a9931f5827516673123f","first_computed_at":"2026-07-05T11:00:53.584551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:53.584551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDlZ+l2t2aVm40T4vqcA9PcjyhFXIZUXVcr9tdPIzrpv5Q0wy5182DG5PkuDju2JwwhAknLUOmyCiKvKaJyiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:53.585172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a903cb908f0bd7f9789eeab998a81f4519d1f09fd2070861d19e1ae8168bf69","sha256:4cf72ed7418a31c683eb0ccdf66475f5558b190a4514d53e8e607b44b93b7cd8"],"state_sha256":"6106e774817cd87316f57e0a51c7ea048597d68e9f888b537373dc4c73c74185"}