{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SYQIQXUOXODL432WKAQDJIBCV7","short_pith_number":"pith:SYQIQXUO","schema_version":"1.0","canonical_sha256":"9620885e8ebb86be6f56502034a022afdb07fcaae09a5b23ed9913f044cbdac8","source":{"kind":"arxiv","id":"2504.03153","version":1},"attestation_state":"computed","paper":{"title":"MORAL: A Multimodal Reinforcement Learning Framework for Decision Making in Autonomous Laboratories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arvind Ramanathan, Natalie Tirabassi, Sathish A. P. Kumar, Sumit Jha","submitted_at":"2025-04-04T04:15:52Z","abstract_excerpt":"We propose MORAL (a multimodal reinforcement learning framework for decision making in autonomous laboratories) that enhances sequential decision-making in autonomous robotic laboratories through the integration of visual and textual inputs. Using the BridgeData V2 dataset, we generate fine-tuned image captions with a pretrained BLIP-2 vision-language model and combine them with visual features through an early fusion strategy. The fused representations are processed using Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) agents. Experimental results demonstrate that multimodal agent"},"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":"2504.03153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T04:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"ebe24c656e23a01bd88551509689a2f36a6af690dff106b11fde01c7f025e1a2","abstract_canon_sha256":"cc9eac640d4ca5d0f8cc5753b6bb00eb78a08f464242061a23caecf8ca7eb39d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:27.320717Z","signature_b64":"AQ4DuAUG0YdaAgWxEfGZkYXKWuUlAc3/G28MlL+pG3xn2WVuWI8EgCXk0JafQ/Z3rdEXIcALyx3rW0FoEOluBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9620885e8ebb86be6f56502034a022afdb07fcaae09a5b23ed9913f044cbdac8","last_reissued_at":"2026-07-05T10:44:27.320283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:27.320283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MORAL: A Multimodal Reinforcement Learning Framework for Decision Making in Autonomous Laboratories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arvind Ramanathan, Natalie Tirabassi, Sathish A. P. Kumar, Sumit Jha","submitted_at":"2025-04-04T04:15:52Z","abstract_excerpt":"We propose MORAL (a multimodal reinforcement learning framework for decision making in autonomous laboratories) that enhances sequential decision-making in autonomous robotic laboratories through the integration of visual and textual inputs. Using the BridgeData V2 dataset, we generate fine-tuned image captions with a pretrained BLIP-2 vision-language model and combine them with visual features through an early fusion strategy. The fused representations are processed using Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) agents. Experimental results demonstrate that multimodal agent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03153","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/2504.03153/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":"2504.03153","created_at":"2026-07-05T10:44:27.320355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03153v1","created_at":"2026-07-05T10:44:27.320355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03153","created_at":"2026-07-05T10:44:27.320355+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYQIQXUOXODL","created_at":"2026-07-05T10:44:27.320355+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYQIQXUOXODL432W","created_at":"2026-07-05T10:44:27.320355+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYQIQXUO","created_at":"2026-07-05T10:44:27.320355+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/SYQIQXUOXODL432WKAQDJIBCV7","json":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7.json","graph_json":"https://pith.science/api/pith-number/SYQIQXUOXODL432WKAQDJIBCV7/graph.json","events_json":"https://pith.science/api/pith-number/SYQIQXUOXODL432WKAQDJIBCV7/events.json","paper":"https://pith.science/paper/SYQIQXUO"},"agent_actions":{"view_html":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7","download_json":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7.json","view_paper":"https://pith.science/paper/SYQIQXUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03153&json=true","fetch_graph":"https://pith.science/api/pith-number/SYQIQXUOXODL432WKAQDJIBCV7/graph.json","fetch_events":"https://pith.science/api/pith-number/SYQIQXUOXODL432WKAQDJIBCV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7/action/storage_attestation","attest_author":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7/action/author_attestation","sign_citation":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7/action/citation_signature","submit_replication":"https://pith.science/pith/SYQIQXUOXODL432WKAQDJIBCV7/action/replication_record"}},"created_at":"2026-07-05T10:44:27.320355+00:00","updated_at":"2026-07-05T10:44:27.320355+00:00"}