{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PL44FVL6VLJWQUS4COAR77Z3IG","short_pith_number":"pith:PL44FVL6","schema_version":"1.0","canonical_sha256":"7af9c2d57eaad368525c13811fff3b41ac587e67c11a628bcbd690222338ed86","source":{"kind":"arxiv","id":"2607.00483","version":1},"attestation_state":"computed","paper":{"title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kuan-Chen Chen, Min-Chun Hu, Wei-Fang Sun, Winston Chen","submitted_at":"2026-07-01T06:11:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T06:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"17fd41e46574f6872c738bc02d4b4d4b39967a1ce58f451e0e83ca2a1c33b685","abstract_canon_sha256":"574fc60bae100ea8a7a835435c2a5fd8fe98e5aa27546f9f11c40e2a74945ecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:44.679574Z","signature_b64":"BWk2dNKbJDQwDKcBqjeuSmZHBnb6Z0JmbIcDdiYJL+d9Q8wBe1P0jj2jN9Kl6LoO8HtZ4FDq9acoi5UZvMyfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7af9c2d57eaad368525c13811fff3b41ac587e67c11a628bcbd690222338ed86","last_reissued_at":"2026-07-02T01:17:44.679151Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:44.679151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kuan-Chen Chen, Min-Chun Hu, Wei-Fang Sun, Winston Chen","submitted_at":"2026-07-01T06:11:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00483","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/2607.00483/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00483","created_at":"2026-07-02T01:17:44.679214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00483v1","created_at":"2026-07-02T01:17:44.679214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00483","created_at":"2026-07-02T01:17:44.679214+00:00"},{"alias_kind":"pith_short_12","alias_value":"PL44FVL6VLJW","created_at":"2026-07-02T01:17:44.679214+00:00"},{"alias_kind":"pith_short_16","alias_value":"PL44FVL6VLJWQUS4","created_at":"2026-07-02T01:17:44.679214+00:00"},{"alias_kind":"pith_short_8","alias_value":"PL44FVL6","created_at":"2026-07-02T01:17:44.679214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG","json":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG.json","graph_json":"https://pith.science/api/pith-number/PL44FVL6VLJWQUS4COAR77Z3IG/graph.json","events_json":"https://pith.science/api/pith-number/PL44FVL6VLJWQUS4COAR77Z3IG/events.json","paper":"https://pith.science/paper/PL44FVL6"},"agent_actions":{"view_html":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG","download_json":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG.json","view_paper":"https://pith.science/paper/PL44FVL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00483&json=true","fetch_graph":"https://pith.science/api/pith-number/PL44FVL6VLJWQUS4COAR77Z3IG/graph.json","fetch_events":"https://pith.science/api/pith-number/PL44FVL6VLJWQUS4COAR77Z3IG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG/action/storage_attestation","attest_author":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG/action/author_attestation","sign_citation":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG/action/citation_signature","submit_replication":"https://pith.science/pith/PL44FVL6VLJWQUS4COAR77Z3IG/action/replication_record"}},"created_at":"2026-07-02T01:17:44.679214+00:00","updated_at":"2026-07-02T01:17:44.679214+00:00"}