{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RAEDOOVGYT6KV7ICRGUG2QRTO2","short_pith_number":"pith:RAEDOOVG","schema_version":"1.0","canonical_sha256":"8808373aa6c4fcaafd0289a86d423376b89426aad5073e31efdab704b7394c9e","source":{"kind":"arxiv","id":"2509.06759","version":1},"attestation_state":"computed","paper":{"title":"Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Campbell Wilson, Janis Dalins, Thanh Thi Nguyen","submitted_at":"2025-09-08T14:47:57Z","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"},"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":"2509.06759","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-08T14:47:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbb2bfeb54f48bf1261f02b3dababd1ae0acadebfc4f8d95187aca46ce208c77","abstract_canon_sha256":"d5bf2d3288101df1b77fdf9d0b00438bad9183185bacbc620a72aa2de39ab20a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:52.443622Z","signature_b64":"xP1WyGvKZHAuAvkt4VZ6zD9RAsIIUz5ZUPjeunQUb+9z1D/Q/mDSZnuR7hKQmwYn8o1nR3jf+m1ttkXLHAU1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8808373aa6c4fcaafd0289a86d423376b89426aad5073e31efdab704b7394c9e","last_reissued_at":"2026-07-05T12:06:52.443129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:52.443129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Campbell Wilson, Janis Dalins, Thanh Thi Nguyen","submitted_at":"2025-09-08T14:47:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06759","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/2509.06759/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":"2509.06759","created_at":"2026-07-05T12:06:52.443202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06759v1","created_at":"2026-07-05T12:06:52.443202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06759","created_at":"2026-07-05T12:06:52.443202+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAEDOOVGYT6K","created_at":"2026-07-05T12:06:52.443202+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAEDOOVGYT6KV7IC","created_at":"2026-07-05T12:06:52.443202+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAEDOOVG","created_at":"2026-07-05T12:06:52.443202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03604","citing_title":"Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2","json":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2.json","graph_json":"https://pith.science/api/pith-number/RAEDOOVGYT6KV7ICRGUG2QRTO2/graph.json","events_json":"https://pith.science/api/pith-number/RAEDOOVGYT6KV7ICRGUG2QRTO2/events.json","paper":"https://pith.science/paper/RAEDOOVG"},"agent_actions":{"view_html":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2","download_json":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2.json","view_paper":"https://pith.science/paper/RAEDOOVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06759&json=true","fetch_graph":"https://pith.science/api/pith-number/RAEDOOVGYT6KV7ICRGUG2QRTO2/graph.json","fetch_events":"https://pith.science/api/pith-number/RAEDOOVGYT6KV7ICRGUG2QRTO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2/action/storage_attestation","attest_author":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2/action/author_attestation","sign_citation":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2/action/citation_signature","submit_replication":"https://pith.science/pith/RAEDOOVGYT6KV7ICRGUG2QRTO2/action/replication_record"}},"created_at":"2026-07-05T12:06:52.443202+00:00","updated_at":"2026-07-05T12:06:52.443202+00:00"}