{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RAEDOOVGYT6KV7ICRGUG2QRTO2","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":"d5bf2d3288101df1b77fdf9d0b00438bad9183185bacbc620a72aa2de39ab20a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-08T14:47:57Z","title_canon_sha256":"dbb2bfeb54f48bf1261f02b3dababd1ae0acadebfc4f8d95187aca46ce208c77"},"schema_version":"1.0","source":{"id":"2509.06759","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06759","created_at":"2026-07-05T12:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06759v1","created_at":"2026-07-05T12:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06759","created_at":"2026-07-05T12:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"RAEDOOVGYT6K","created_at":"2026-07-05T12:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"RAEDOOVGYT6KV7IC","created_at":"2026-07-05T12:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"RAEDOOVG","created_at":"2026-07-05T12:06:52Z"}],"graph_snapshots":[{"event_id":"sha256:0d81efe39deaef6bf2a59b915cb1b570dfaa2d7979af9aac2cf491c847013869","target":"graph","created_at":"2026-07-05T12:06:52Z","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/2509.06759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While large-scale pretraining has driven substantial progress, fine-tuning these models for aligning with human values or engaging in specific tasks or behaviors remains a critical challenge. Deep Reinforcement Learning (DRL) and Direct Preference Optimization (DPO) offer promising frameworks for this aligning process. While DRL enables models to optimize actions us","authors_text":"Campbell Wilson, Janis Dalins, Thanh Thi Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-08T14:47:57Z","title":"Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06759","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:b69286eadfedbab4bb2fa29ebb5ff72cb0ab574cecfbf354d549076b0acf04c0","target":"record","created_at":"2026-07-05T12:06:52Z","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":"d5bf2d3288101df1b77fdf9d0b00438bad9183185bacbc620a72aa2de39ab20a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-08T14:47:57Z","title_canon_sha256":"dbb2bfeb54f48bf1261f02b3dababd1ae0acadebfc4f8d95187aca46ce208c77"},"schema_version":"1.0","source":{"id":"2509.06759","kind":"arxiv","version":1}},"canonical_sha256":"8808373aa6c4fcaafd0289a86d423376b89426aad5073e31efdab704b7394c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8808373aa6c4fcaafd0289a86d423376b89426aad5073e31efdab704b7394c9e","first_computed_at":"2026-07-05T12:06:52.443129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:52.443129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xP1WyGvKZHAuAvkt4VZ6zD9RAsIIUz5ZUPjeunQUb+9z1D/Q/mDSZnuR7hKQmwYn8o1nR3jf+m1ttkXLHAU1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:52.443622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06759","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b69286eadfedbab4bb2fa29ebb5ff72cb0ab574cecfbf354d549076b0acf04c0","sha256:0d81efe39deaef6bf2a59b915cb1b570dfaa2d7979af9aac2cf491c847013869"],"state_sha256":"ebb29401f1e4534fa09e3f29d6272d26de68ac2e4bf2f422a05ac61e74374e78"}