{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CITUR6V34ICKTZOOXR56DFEPOZ","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":"29e8e993f6c0b1dbb2ae21a84a5ed361c305dc5865948c4d460f57bc57271314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T16:15:12Z","title_canon_sha256":"db8d1185ad101f99de6428827cd55965063e98890617922e34fa330c1943b20a"},"schema_version":"1.0","source":{"id":"2608.03875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03875","created_at":"2026-08-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03875v1","created_at":"2026-08-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03875","created_at":"2026-08-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"CITUR6V34ICK","created_at":"2026-08-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"CITUR6V34ICKTZOO","created_at":"2026-08-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"CITUR6V3","created_at":"2026-08-05T01:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:b22e8da76f7f7e49d6a151117b882ef8e02e73f8d060bc6e9f57cf2f9c7140ae","target":"graph","created_at":"2026-08-05T01:37:18Z","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/2608.03875/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 bottleneck in Reinforcement Learning (RL). Recent work uses large foundation Vision-Language Models (VLMs) as reward models, computing text-observation similarity to bypass manual reward engineering. Although promising, these rewards are often noisy and unreliable, limiting their direct utility during deployment. We present Structure-Aware Fine-Tuning (SAFT), a simple, self-supervised method that refines these imperfect reward signals online without access to ground-truth supervision. SAFT leverages intrinsic structural priors to regularize ","authors_text":"Andreas Krause, Chenhao Li, Pyrros Koussios, Xin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T16:15:12Z","title":"Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03875","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":"sha256:3afb01d260438b875a8d74df739fb7ef9e6c6b3d6de9d50ec6ff2c5d20f30b8f","target":"record","created_at":"2026-08-05T01:37:18Z","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":"29e8e993f6c0b1dbb2ae21a84a5ed361c305dc5865948c4d460f57bc57271314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T16:15:12Z","title_canon_sha256":"db8d1185ad101f99de6428827cd55965063e98890617922e34fa330c1943b20a"},"schema_version":"1.0","source":{"id":"2608.03875","kind":"arxiv","version":1}},"canonical_sha256":"122748fabbe204a9e5cebc7be1948f7650ff40f1f0921e3e347ddbd7836d9eab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"122748fabbe204a9e5cebc7be1948f7650ff40f1f0921e3e347ddbd7836d9eab","first_computed_at":"2026-08-05T01:37:18.099072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:18.099072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qkHHte8xTnRlCXEAVSMWNlKjf/bUOWHy4Ow8P5JQCQQjyg8v7HAqWNCnEHVAO7FHOQgc21NDlWgaaSAE7aAOBw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:18.100455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3afb01d260438b875a8d74df739fb7ef9e6c6b3d6de9d50ec6ff2c5d20f30b8f","sha256:b22e8da76f7f7e49d6a151117b882ef8e02e73f8d060bc6e9f57cf2f9c7140ae"],"state_sha256":"8b74346a0207eafeb74d6ad63a82052acc994e3f9e51488d1081fc9beeb6eebd"}