{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3C24JPFCJF3IDQJIWXJ7KVJHJN","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":"7975b8ebe4dc861c6b2ed3b454269c9894d032bbded93c35e116597462d38a35","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-26T09:52:25Z","title_canon_sha256":"b2e6ac1312dcff179ed81e2f37acb8252ffe786d652e0e958c4a4219758027c4"},"schema_version":"1.0","source":{"id":"2505.19769","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19769","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19769v2","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19769","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"3C24JPFCJF3I","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"3C24JPFCJF3IDQJI","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"3C24JPFC","created_at":"2026-07-05T11:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:e076fc2e9fd0574e06ca1173a346a6714c872e0890f844d3a1037ad76dc50d92","target":"graph","created_at":"2026-07-05T11:26:04Z","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/2505.19769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing scalable and generalizable reward engineering for reinforcement learning (RL) is crucial for creating general-purpose agents, especially in the challenging domain of robotic manipulation. While recent advances in reward engineering with Vision-Language Models (VLMs) have shown promise, their sparse reward nature significantly limits sample efficiency. This paper introduces TeViR, a novel method that leverages a pre-trained text-to-video diffusion model to generate dense rewards by comparing the predicted image sequence with current observations. Experimental results across 11 comple","authors_text":"Dongbin Zhao, Haoran Li, Haowei Wen, Yuhui Chen, Zhennan Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-26T09:52:25Z","title":"TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19769","kind":"arxiv","version":2},"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:aacd51002670501ee1a22a48ae1006f6306803d01f72bd19d808a82a34e44f71","target":"record","created_at":"2026-07-05T11:26:04Z","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":"7975b8ebe4dc861c6b2ed3b454269c9894d032bbded93c35e116597462d38a35","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-26T09:52:25Z","title_canon_sha256":"b2e6ac1312dcff179ed81e2f37acb8252ffe786d652e0e958c4a4219758027c4"},"schema_version":"1.0","source":{"id":"2505.19769","kind":"arxiv","version":2}},"canonical_sha256":"d8b5c4bca2497681c128b5d3f555274b60d14cf07626e0094f89891ac5bc4e96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8b5c4bca2497681c128b5d3f555274b60d14cf07626e0094f89891ac5bc4e96","first_computed_at":"2026-07-05T11:26:04.781056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:04.781056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kRcBaByi9TDGXtMN2BWQQetVPE3bvvZWywo4ILflNck3sl8iIt91GlVt/EXXDwqcWla7ccAZst3ds0/tILxBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:04.781562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19769","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aacd51002670501ee1a22a48ae1006f6306803d01f72bd19d808a82a34e44f71","sha256:e076fc2e9fd0574e06ca1173a346a6714c872e0890f844d3a1037ad76dc50d92"],"state_sha256":"372e94a2bebe2c51fa1707b7cef7bcca4849f7a12624b879f8a58ea350b413f6"}