{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B357M62R5Q7MF7Z25QIU3FVKN6","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":"78c4cb09db3cbaacb5322c1e5e90d1c6b4aa4dacb21c3db576951e714fa89598","cross_cats_sorted":["cs.HC","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T01:51:27Z","title_canon_sha256":"6ce926aeab3ced030b4359e6310e8cafec99ed034ea3daf1cdc7f658e73b3095"},"schema_version":"1.0","source":{"id":"2503.13817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13817","created_at":"2026-07-05T10:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13817v1","created_at":"2026-07-05T10:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13817","created_at":"2026-07-05T10:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"B357M62R5Q7M","created_at":"2026-07-05T10:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"B357M62R5Q7MF7Z2","created_at":"2026-07-05T10:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"B357M62R","created_at":"2026-07-05T10:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:973d341b6c4fdf89ae39630dd7f9011837e119170fa1b752256b9fff74d72284","target":"graph","created_at":"2026-07-05T10:33:19Z","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/2503.13817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative feedback rather than hand-crafted signals, yet scaling human annotations remains challenging. Recent work uses Vision-Language Models (VLMs) to automate preference labeling, but a single final-state image generally fails to capture the agent's full motion. In this paper, we present a two-part solution that both improves feedback accuracy and better aligns reward le","authors_text":"Amisha Bhaskar, Amrit Bedi, Anukriti Singh, Peihong Yu, Pratap Tokekar, Ruthwik Dasyam, Souradip Chakraborty","cross_cats":["cs.HC","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T01:51:27Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13817","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":"sha256:5c20674e00548d51d474c1c93e406160e05507a72ada96203ced70540ad9c3cb","target":"record","created_at":"2026-07-05T10:33:19Z","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":"78c4cb09db3cbaacb5322c1e5e90d1c6b4aa4dacb21c3db576951e714fa89598","cross_cats_sorted":["cs.HC","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T01:51:27Z","title_canon_sha256":"6ce926aeab3ced030b4359e6310e8cafec99ed034ea3daf1cdc7f658e73b3095"},"schema_version":"1.0","source":{"id":"2503.13817","kind":"arxiv","version":1}},"canonical_sha256":"0efbf67b51ec3ec2ff3aec114d96aa6fbe7be788701cc5084f3ff7d7c75e7939","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0efbf67b51ec3ec2ff3aec114d96aa6fbe7be788701cc5084f3ff7d7c75e7939","first_computed_at":"2026-07-05T10:33:19.111953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:19.111953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLoCurt8MI7qItqRWpANGtTBpAP+qZN1M9DClLHFT/L+ToNa1zFEKd89W+KxRdmvIOzb57JUCx05M55azylbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:19.112447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c20674e00548d51d474c1c93e406160e05507a72ada96203ced70540ad9c3cb","sha256:973d341b6c4fdf89ae39630dd7f9011837e119170fa1b752256b9fff74d72284"],"state_sha256":"cbc0594af83307bdcddd2febdd6df22c56d805e13b83704ad41fac73c3aa7a36"}