{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PL44FVL6VLJWQUS4COAR77Z3IG","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":"574fc60bae100ea8a7a835435c2a5fd8fe98e5aa27546f9f11c40e2a74945ecc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T06:11:59Z","title_canon_sha256":"17fd41e46574f6872c738bc02d4b4d4b39967a1ce58f451e0e83ca2a1c33b685"},"schema_version":"1.0","source":{"id":"2607.00483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00483","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00483v1","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00483","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"PL44FVL6VLJW","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"PL44FVL6VLJWQUS4","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"PL44FVL6","created_at":"2026-07-02T01:17:44Z"}],"graph_snapshots":[{"event_id":"sha256:94855924da9ebe1cf2acf31caca584853e6e8af2b09b6e632bf44a59255606c6","target":"graph","created_at":"2026-07-02T01:17:44Z","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/2607.00483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective reward functions remains a major challenge in reinforcement learning (RL), particularly in open-ended environments where task goals are abstract and difficult to quantify. In this work, we present VLM-AR3L, a framework that leverages Vision-Language Models (VLMs) to provide both absolute and relative rewards for RL. VLM-AR3L interprets an agent's visual observations in the context of a natural language task goal, and learns both absolute and relative rewards from VLM-generated preference labels. The absolute reward model predicts scalar evaluations for individual states, wh","authors_text":"Kuan-Chen Chen, Min-Chun Hu, Wei-Fang Sun, Winston Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T06:11:59Z","title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00483","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":"sha256:992edc8e4e72b1dbdd7657547b46f9d1d65e028ba3b5270611b63b2054ff9107","target":"record","created_at":"2026-07-02T01:17:44Z","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":"574fc60bae100ea8a7a835435c2a5fd8fe98e5aa27546f9f11c40e2a74945ecc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T06:11:59Z","title_canon_sha256":"17fd41e46574f6872c738bc02d4b4d4b39967a1ce58f451e0e83ca2a1c33b685"},"schema_version":"1.0","source":{"id":"2607.00483","kind":"arxiv","version":1}},"canonical_sha256":"7af9c2d57eaad368525c13811fff3b41ac587e67c11a628bcbd690222338ed86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7af9c2d57eaad368525c13811fff3b41ac587e67c11a628bcbd690222338ed86","first_computed_at":"2026-07-02T01:17:44.679151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:44.679151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BWk2dNKbJDQwDKcBqjeuSmZHBnb6Z0JmbIcDdiYJL+d9Q8wBe1P0jj2jN9Kl6LoO8HtZ4FDq9acoi5UZvMyfAg==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:44.679574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:992edc8e4e72b1dbdd7657547b46f9d1d65e028ba3b5270611b63b2054ff9107","sha256:94855924da9ebe1cf2acf31caca584853e6e8af2b09b6e632bf44a59255606c6"],"state_sha256":"7f62a0078122eba10599cea0f68a13091d326f7a333c456c6362fb84fc672c05"}